© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10998
    Prev
    Next
    INDEX
    Explanations

    code diffs.

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Anfang
    -0.56
     before
    -0.49
     mid
    -0.48
    "
    -0.48
    <eos>
    -0.47
    mid
    -0.47
    ~
    -0.46
     My
    -0.46
    le
    -0.46
    My
    -0.46
    POSITIVE LOGITS
    AndEndTag
    1.02
     Monfieur
    0.99
     itſelf
    0.99
     Efq
    0.96
     myſelf
    0.95
     Theſe
    0.90
     Majefty
    0.90
     CreateTagHelper
    0.89
     againſt
    0.88
     GenerationType
    0.87
    Activations Density 2.798%

    No Known Activations