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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1107
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences, opinions and observations, especially when made by the narrator ("I" or "you")

    oai_token-act-pair · gemini-2.0-flash

    looking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ⓧ
    -0.70
    SPATH
    -0.65
    DotNetBar
    -0.63
     gynhyrchwyd
    -0.56
     vectorielles
    -0.53
     Antiquities
    -0.52
    rawDesc
    -0.52
    AddComponent
    -0.51
    脚注の使い方
    -0.50
    HSSF
    -0.50
    POSITIVE LOGITS
     looking
    2.45
     look
    2.33
    looking
    2.17
     Looking
    2.14
    Looking
    2.08
    look
    2.03
     looked
    2.03
     looks
    2.02
     Look
    2.00
     LOOKING
    1.98
    Activations Density 6.604%

    No Known Activations