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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131166
    Prev
    Next
    INDEX
    Explanations

    abomination or biomass

    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_1_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
    I
    1.26
     fable
    1.03
    𝗟
    1.02
     inhomogeneities
    0.98
    kannya
    0.95
     heuristics
    0.89
    V
    0.89
    gover
    0.88
    ில்
    0.88
     dividends
    0.88
    POSITIVE LOGITS
    9
    1.20
    رك
    1.16
    ارة
    1.16
    其他
    1.15
    的
    1.14
    م
    1.13
    ции
    1.11
     trochu
    1.10
    ني
    1.09
    مة
    1.09
    Activations Density 0.000%

    No Known Activations