© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11169
    Prev
    Next
    INDEX
    Explanations

    legal citation numbers

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     
    -0.77
     I
    -0.54
     S
    -0.52
     C
    -0.51
     P
    -0.50
     (
    -0.50
     B
    -0.49
     \
    -0.49
     O
    -0.48
     С
    -0.48
    POSITIVE LOGITS
     Efq
    0.88
     Reſ
    0.82
     myſelf
    0.81
     Monfieur
    0.79
     purpoſe
    0.77
     houſe
    0.76
     raiſ
    0.75
     occaf
    0.74
     Houſe
    0.73
     بيها
    0.73
    Activations Density 0.466%

    No Known Activations