© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14034
    Prev
    Next
    INDEX
    Explanations

    code documentation and comments within code, particularly those using specific formatting conventions.

    oai_token-act-pair · gemini-2.0-flash

    functions related to programming documentation

    np_token-act-pair-logits · gpt-4o-mini

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.74
    addPreferredGap
    -0.73
     Administrativna
    -0.69
     Pingback
    -0.63
    ViewFeatures
    -0.62
     defaultstate
    -0.60
    uxxxx
    -0.59
     volcanoes
    -0.58
    enumii
    -0.58
     *)__
    -0.57
    POSITIVE LOGITS
     Given
    0.58
     Has
    0.49
    Given
    0.49
     This
    0.48
     given
    0.47
    given
    0.46
     Returns
    0.45
     recovers
    0.45
    bbles
    0.43
     GIVEN
    0.43
    Activations Density 3.071%

    No Known Activations