© 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. 11322
    Prev
    Next
    INDEX
    Explanations

    references to remembering

    oai_token-act-pair · gemini-2.0-flash

    words related to membership

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

    remembering

    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
     pulpit
    -0.53
    rators
    -0.50
     sermons
    -0.50
    dash
    -0.48
     scrubs
    -0.48
     forget
    -0.46
     Messer
    -0.45
     LUMP
    -0.44
    matory
    -0.44
     camps
    -0.44
    POSITIVE LOGITS
    member
    0.71
    CloseOperation
    0.69
    rungsseite
    0.69
     مرئيه
    0.68
    membered
    0.66
     member
    0.65
    ollection
    0.62
    members
    0.61
     Treasure
    0.59
     disambiguazione
    0.58
    Activations Density 0.497%

    No Known Activations