© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3911
    Prev
    Next
    INDEX
    Explanations

    references to years

    oai_token-act-pair · gemini-2.0-flash

    Common short words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -1.70
     myſelf
    -1.64
     itſelf
    -1.60
     Efq
    -1.59
     Jefus
    -1.55
     Houſe
    -1.55
     Monfieur
    -1.55
     raiſ
    -1.48
     themſelves
    -1.46
     Diſ
    -1.46
    POSITIVE LOGITS
     of
    0.67
     to
    0.60
     in
    0.56
     
    0.54
     $
    0.52
     the
    0.50
    $
    0.49
     for
    0.48
     or
    0.47
     and
    0.47
    Activations Density 5.210%

    No Known Activations