© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6649
    Prev
    Next
    INDEX
    Explanations

    the word "Title"

    oai_token-act-pair · gemini-2.0-flash

    Title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Theſe
    -1.42
     itſelf
    -1.32
     themſelves
    -1.25
     myſelf
    -1.24
     Efq
    -1.24
     Houſe
    -1.18
     raiſ
    -1.16
     ―――――
    -1.15
     poffible
    -1.13
     faſt
    -1.12
    POSITIVE LOGITS
     it
    0.79
     the
    0.77
     in
    0.77
     he
    0.76
     an
    0.73
     a
    0.71
     that
    0.66
     to
    0.61
     for
    0.59
     at
    0.59
    Activations Density 1.680%

    No Known Activations