© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13480
    Prev
    Next
    INDEX
    Explanations

    numerical values, especially percentages and other statistics

    oai_token-act-pair · gemini-2.0-flash

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     MainAxisSize
    -0.61
    COLLE
    -0.59
    <bos>
    -0.57
    __':
    -0.57
     виправивши
    -0.55
    __":
    -0.54
    ✨:
    -0.53
    mord
    -0.52
    kháu
    -0.52
     ?>>
    -0.52
    POSITIVE LOGITS
     houſe
    0.73
     ſtate
    0.62
     Anſ
    0.60
    ByExample
    0.56
     reaſon
    0.56
     juſ
    0.56
     pleaſure
    0.55
     perſon
    0.54
     anſ
    0.53
     ſte
    0.52
    Activations Density 7.326%

    No Known Activations