© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    words related to shooting, filming, or being shot, and sports teams

    oai_token-act-pair · gemini-2.0-flash

    shooting/filming

    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
     shoot
    -2.92
     shot
    -2.86
     shooting
    -2.83
     shoots
    -2.64
     Shoot
    -2.61
     Shot
    -2.59
     Shooting
    -2.55
    Shooting
    -2.53
     shots
    -2.52
    shot
    -2.52
    POSITIVE LOGITS
    JsonHelper
    0.54
     pulumi
    0.54
    oredCriteria
    0.52
    lexia
    0.52
    ("/:
    0.46
     ExecuteAsync
    0.45
     MainAxisSize
    0.45
     هيا
    0.44
     couvercle
    0.43
    RectangleBorder
    0.43
    Activations Density 1.900%

    No Known Activations