© 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. 12345
    Prev
    Next
    INDEX
    Explanations

    references to specific times

    oai_token-act-pair · gemini-2.0-flash

    say "time"

    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
     باخ
    -0.60
    이터
    -0.47
     casing
    -0.46
    şim
    -0.46
     vertu
    -0.46
    ല്ല
    -0.44
    AMAR
    -0.43
    वा
    -0.43
     Corde
    -0.43
    صاد
    -0.42
    POSITIVE LOGITS
    tagext
    0.81
    EndContext
    0.78
     kasarigan
    0.72
     '\\;'
    0.71
    GraphicsUnit
    0.69
    awtextra
    0.68
    DeleteBehavior
    0.68
    OGND
    0.67
    matchCondition
    0.66
    WindowConstants
    0.66
    Activations Density 4.425%

    No Known Activations