© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9172
    Prev
    Next
    INDEX
    Explanations

    percentages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     Ona
    0.71
    TextColor
    0.70
    醣
    0.70
    <unused2137>
    0.68
     ide
    0.68
    Impl
    0.68
     envolve
    0.67
     छोट
    0.66
    IOD
    0.66
     Dri
    0.65
    POSITIVE LOGITS
     percent
    1.01
    Percent
    0.84
     Percent
    0.77
     PERCENT
    0.76
     Prozent
    0.75
     per
    0.73
     &
    0.73
    percent
    0.72
     persen
    0.72
     za
    0.65
    Activations Density 0.047%

    No Known Activations