© 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. 14792
    Prev
    Next
    INDEX
    Explanations

    numerical date or percentage information

    oai_token-act-pair · gemini-2.0-flash

    Technical/legal/scientific documents

    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
    3
    -0.79
    ３
    -0.59
    2
    -0.59
     III
    -0.47
     ३
    -0.46
     Thirty
    -0.46
    ing
    -0.45
    RequestHandler
    -0.45
     שוליים
    -0.44
    4
    -0.44
    POSITIVE LOGITS
    TabStop
    0.71
    Diwedd
    0.64
     onOptions
    0.61
    getMenuInflater
    0.60
    nocache
    0.59
    styleable
    0.59
     doInBackground
    0.56
     &___
    0.56
    complexContent
    0.56
    ArgsConstructor
    0.54
    Activations Density 9.335%

    No Known Activations