© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3121
    Prev
    Next
    INDEX
    Explanations

    code, particularly java or similar, including keywords, classes, and interfaces.

    oai_token-act-pair · gemini-2.0-flash

    class

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    be
    -0.48
    3
    -0.47
    1
    -0.47
    array
    -0.47
    bel
    -0.46
    de
    -0.46
    2
    -0.45
    5
    -0.45
    ip
    -0.44
    vi
    -0.44
    POSITIVE LOGITS
    Personendaten
    1.13
    تقاوى
    1.02
     Walkover
    1.00
    enumii
    0.97
    tagHelperRunner
    0.88
    ValueStyle
    0.88
     صوتيه
    0.87
    tvguidetime
    0.86
    AddTagHelper
    0.84
    Архівовано
    0.83
    Activations Density 2.248%

    No Known Activations