Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9580
    Prev
    Next
    INDEX
    Explanations

    all sorts of random punctuation within sentences

    oai_token-act-pair · gemini-2.0-flash

    dashes/quotation marks

    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
     and
    -1.51
    AndEndTag
    -0.89
    fromnode
    -0.71
     insuffisamment
    -0.70
    enumii
    -0.70
     or
    -0.68
    性和
    -0.65
    cshtml
    -0.63
     &
    -0.62
     betweenstory
    -0.62
    POSITIVE LOGITS
    AND
    1.48
    and
    1.30
    ands
    0.98
    ANDS
    0.93
    andam
    0.82
    andai
    0.81
    andis
    0.79
    andha
    0.78
    anden
    0.77
    ANDED
    0.77
    Activations Density 10.631%

    No Known Activations