© 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. 4082
    Prev
    Next
    INDEX
    Explanations

    technical writing describing coatings and their properties.

    oai_token-act-pair · gemini-2.0-flash

    coatings and surface treatments

    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
     coated
    -1.30
     coating
    -1.22
    coat
    -1.20
     Coated
    -1.19
     coat
    -1.19
     Coating
    -1.19
    coated
    -1.16
    Coat
    -1.13
    coating
    -1.13
     Coat
    -1.09
    POSITIVE LOGITS
    TypedDataSet
    0.59
     Públicas
    0.58
     createSlice
    0.50
    ყ
    0.49
     contextLoads
    0.48
     ErrInvalid
    0.48
     tầm
    0.47
    modb
    0.47
     EClass
    0.47
     drenaje
    0.46
    Activations Density 2.740%

    No Known Activations