© 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. 7900
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     Pills
    -0.54
     Roskov
    -0.54
    Geplaatst
    -0.49
     POSTAGE
    -0.49
     “
    -0.48
    Autoritní
    -0.47
    nteral
    -0.47
    idosis
    -0.47
    batsman
    -0.47
    umab
    -0.47
    POSITIVE LOGITS
     marquées
    0.69
     către
    0.68
     traditionnels
    0.65
     illustrazione
    0.65
     sélectionnés
    0.64
     penyimpanan
    0.64
     avoient
    0.64
     représenté
    0.63
     varandra
    0.63
     amélior
    0.61
    Activations Density 30.946%

    No Known Activations