© 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-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167191
    Prev
    Next
    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    (“
    0.52
     (“
    0.41
    @{
    0.40
    新闻
    0.38
    殄
    0.38
     “…
    0.36
    ença
    0.36
    </h1>
    0.36
     $@
    0.35
    şti
    0.35
    POSITIVE LOGITS
     angel
    0.71
     Angel
    0.68
     angels
    0.64
     Ángel
    0.63
    Angel
    0.62
     Angels
    0.61
    angel
    0.60
     ang
    0.59
    Ang
    0.59
     áng
    0.57
    Activations Density 0.000%

    No Known Activations