© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30563
    Prev
    Next
    INDEX
    Explanations

    idol, Id, sinners, duality, fragmentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     внешней
    0.40
    envelope
    0.39
    癬
    0.39
    โมง
    0.39
    Envelope
    0.38
     Envelope
    0.38
    isHidden
    0.38
     exogenous
    0.38
    铬
    0.38
    ermodel
    0.37
    POSITIVE LOGITS
     idol
    0.77
     idolat
    0.73
     idols
    0.68
     Idol
    0.67
    idol
    0.67
     Id
    0.54
    Id
    0.53
    偶像
    0.52
    id
    0.48
     sir
    0.45
    Activations Density 0.047%

    No Known Activations