© 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. 6707
    Prev
    Next
    INDEX
    Explanations

    code related to models

    oai_token-act-pair · gemini-2.0-flash

    Research models

    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
     model
    -2.17
     Model
    -1.99
    model
    -1.96
    Model
    -1.83
     MODEL
    -1.69
     modelo
    -1.49
    MODEL
    -1.48
     modèle
    -1.46
     모델
    -1.40
     modello
    -1.32
    POSITIVE LOGITS
    comuna
    0.48
    JKLM
    0.48
     везе
    0.47
     rope
    0.46
    rope
    0.46
     endfor
    0.45
    endgroup
    0.44
    eqref
    0.44
     Stich
    0.44
    enada
    0.44
    Activations Density 5.389%

    No Known Activations