© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4249
    Prev
    Next
    INDEX
    Explanations

    a combination of numbers and units of measurement (temperature, altitude, financial values, patent numbers)

    oai_token-act-pair · gemini-2.0-flash

    references and codes

    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
    rrggbb
    -0.73
     thousands
    -0.59
    principalColumn
    -0.56
    ImageContext
    -0.53
     propOrder
    -0.53
     hundreds
    -0.52
     <=",
    -0.50
     Thousands
    -0.50
    LayoutInflater
    -0.49
     صوتيه
    -0.48
    POSITIVE LOGITS
    twimg
    0.76
    はじめに
    0.71
    bkz
    0.57
    INGS
    0.52
    CPtr
    0.52
    <bos>
    0.51
    Nouvelle
    0.51
    IsContent
    0.50
    indexOf
    0.50
    mspace
    0.49
    Activations Density 31.064%

    No Known Activations