© 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. 6811
    Prev
    Next
    INDEX
    Explanations

    references to bands, musicians, and musical works.

    oai_token-act-pair · gemini-2.0-flash

    Writing, media descriptions

    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
    CloseOperation
    -0.69
    脚注の使い方
    -0.66
     Roskov
    -0.63
    saraba
    -0.61
    ="#"><
    -0.57
    üyada
    -0.55
    WriteTagHelper
    -0.55
    oa̍t
    -0.55
    RectangleBorder
    -0.55
     snippetHide
    -0.54
    POSITIVE LOGITS
    ProcessEvent
    0.50
     filas
    0.50
    srcs
    0.50
    ofType
    0.50
     CWE
    0.48
    BASEPATH
    0.48
    piers
    0.46
    spesies
    0.46
    DIRS
    0.45
     nahilalakip
    0.45
    Activations Density 4.186%

    No Known Activations