© 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. 8848
    Prev
    Next
    INDEX
    Explanations

    words associated with time, direction, desire, and intent such as "forward", "finding", "going" and "up".

    oai_token-act-pair · gemini-2.0-flash

    Something went wrong

    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
    ंदीखरीदारी
    -0.54
    Model
    -0.52
     Model
    -0.51
    Mutability
    -0.50
    Semitism
    -0.49
     Marie
    -0.49
     Integration
    -0.48
     Muir
    -0.47
     Jo
    -0.47
     Maurer
    -0.47
    POSITIVE LOGITS
     Unto
    0.73
     defaultstate
    0.73
     متعلقه
    0.71
     againſt
    0.67
     HasFactory
    0.66
    UrlResolution
    0.60
    RenderAtEndOf
    0.60
     Away
    0.60
     Backward
    0.59
     Carried
    0.59
    Activations Density 14.595%

    No Known Activations