© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6296
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and equations, including the words "for" and "solve".

    oai_token-act-pair · gemini-2.0-flash

    mathematical procedure steps or definitions

    np_token-act-pair-logits · gpt-4o-mini

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     myſelf
    -1.09
     Monfieur
    -1.02
     Theſe
    -0.92
     ſeveral
    -0.91
     purpoſe
    -0.90
     raiſ
    -0.88
     pleaſure
    -0.88
     himſelf
    -0.88
    AnchorStyles
    -0.86
     houſe
    -0.86
    POSITIVE LOGITS
     Step
    0.48
     step
    0.46
     its
    0.45
    Step
    0.45
     A
    0.45
     let
    0.44
     H
    0.44
     Ch
    0.44
     sin
    0.44
     since
    0.43
    Activations Density 10.897%

    No Known Activations