© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6939
    Prev
    Next
    INDEX
    Explanations

    mentions of parts, pieces, division, construction, and assembly

    oai_token-act-pair · gemini-2.0-flash

    pieces

    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
     piece
    -1.88
    piece
    -1.57
     Piece
    -1.51
     PIECE
    -1.49
    Piece
    -1.42
     pieces
    -1.16
     pieza
    -1.13
     Pieces
    -1.11
     pezzo
    -1.10
    PIECE
    -1.10
    POSITIVE LOGITS
    stateProvider
    0.71
    rzost
    0.69
    AutoScaleMode
    0.60
    Geplaatst
    0.59
    AddTagHelper
    0.56
    دانشنامهٔ
    0.54
    Хьажоргаш
    0.53
     оригіналу
    0.53
    Hochspringen
    0.53
    RenderAtEndOf
    0.52
    Activations Density 3.867%

    No Known Activations