© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 440
    Prev
    Next
    INDEX
    Explanations

    context around a personal statement or narrative, often including descriptions of a profession or a skill.

    oai_token-act-pair · gemini-2.0-flash

    say "a" or "an"

    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
    any
    -0.62
    A
    -0.55
    i
    -0.55
    as
    -0.55
    it
    -0.54
    that
    -0.52
    is
    -0.50
    I
    -0.49
     A
    -0.47
    e
    -0.46
    POSITIVE LOGITS
     Efq
    1.31
     Monfieur
    1.27
     Anſ
    1.20
     Theſe
    1.18
     myſelf
    1.17
     itſelf
    1.16
     Reſ
    1.12
     Houſe
    1.09
     Conſ
    1.08
     ſeveral
    1.07
    Activations Density 2.581%

    No Known Activations