© 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. 106802
    Prev
    Next
    INDEX
    Explanations

    Milgram, heads, gram

    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
    aría
    1.12
    ని
    1.08
    ব
    1.07
    },
    1.05
    cepc
    1.04
    ಿಂದ
    1.02
    fähigkeit
    1.02
    ński
    1.01
    വരെ
    1.01
    жив
    1.01
    POSITIVE LOGITS
    л
    1.49
    á
    1.39
     $
    1.30
    ۴
    1.25
     \
    1.20
    ू
    1.09
    ۶
    1.05
    ou
    1.01
    lerin
    1.01
    ۵
    1.01
    Activations Density 0.000%

    No Known Activations