© 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. 6065
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and related terms, also finding a few words related to government

    oai_token-act-pair · gemini-2.0-flash

    dates

    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
    ido
    -0.47
     
    -0.45
    行
    -0.44
    S
    -0.43
    żs
    -0.43
    vars
    -0.42
     dire
    -0.41
    ans
    -0.41
    T
    -0.41
    map
    -0.41
    POSITIVE LOGITS
    +:+
    0.90
    fjspx
    0.88
     الرياضيه
    0.88
     ModelExpression
    0.83
    #+#
    0.81
    Personendaten
    0.80
    bootstrapcdn
    0.78
    featureID
    0.74
    batore
    0.74
     חיצוניים
    0.73
    Activations Density 22.267%

    No Known Activations