© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9760
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of people and systems.

    oai_token-act-pair · gemini-2.0-flash

    positive feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ↵↵
    -0.49
    resten
    -0.46
    offset
    -0.45
     conforman
    -0.43
    FormControl
    -0.43
    rie
    -0.42
     n
    -0.42
     b
    -0.42
    elseif
    -0.42
     Navigator
    -0.40
    POSITIVE LOGITS
    tvguidetime
    0.93
    Portale
    0.91
     MainAxisSize
    0.91
    MLLoader
    0.88
     AttributeSet
    0.84
    DockStyle
    0.83
     فريبيس
    0.82
    #+#
    0.78
    脚注の使い方
    0.77
    !*\
    0.73
    Activations Density 0.508%

    No Known Activations