© 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. 14807
    Prev
    Next
    INDEX
    Explanations

    words related to the design process, human ability, and intent.

    oai_token-act-pair · gemini-2.0-flash

    designed/developed

    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
    UnusedPrivate
    -0.65
     useParams
    -0.54
    esez
    -0.51
     genau
    -0.49
    LookAnd
    -0.48
    InitVars
    -0.46
     الحره
    -0.44
    Fns
    -0.43
     gebruik
    -0.42
    ities
    -0.42
    POSITIVE LOGITS
    bootstrapcdn
    0.66
    ={`/
    0.61
    MigrationBuilder
    0.60
    ếc
    0.58
    desert
    0.57
    StandardCharsets
    0.56
    seido
    0.56
    iglio
    0.55
    DockStyle
    0.55
    gypti
    0.54
    Activations Density 16.712%

    No Known Activations