Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15015
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_19_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ଆ
    0.76
    风险
    0.76
     inne
    0.75
    制度
    0.75
    㔹
    0.75
     venido
    0.74
     சர்
    0.73
    াবিশ
    0.73
     民
    0.72
     soát
    0.72
    POSITIVE LOGITS
    obenzene
    0.65
    лку
    0.64
    mj
    0.64
    amples
    0.63
     آزم
    0.63
     ornamentation
    0.62
    рту
    0.62
    Kent
    0.60
     paintbrush
    0.60
    affected
    0.59
    Activations Density 0.006%

    No Known Activations