© 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. 6220
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and equation-solving contexts

    oai_token-act-pair · gemini-2.0-flash

    say t

    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
     T
    -1.50
    T
    -1.34
     Т
    -1.32
     TT
    -1.28
     Ti
    -1.28
    Ｔ
    -1.21
     TI
    -1.20
     TH
    -1.20
    TT
    -1.18
     TF
    -1.16
    POSITIVE LOGITS
    SharedDtor
    0.56
    COUVER
    0.54
     mergeFrom
    0.51
    EDEFAULT
    0.50
     estekak
    0.46
     Paglinawan
    0.45
    AccessorTable
    0.45
    rungsseite
    0.44
     ModelExpression
    0.43
    Einzelnachweise
    0.43
    Activations Density 32.136%

    No Known Activations