© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132004
    Prev
    Next
    INDEX
    Explanations

    Rosen appended with names/words

    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
    B
    1.02
    し
    0.96
    P
    0.92
    τή
    0.89
    G
    0.89
    X
    0.89
    לי
    0.88
     práct
    0.85
    A
    0.85
    ור
    0.84
    POSITIVE LOGITS
     as
    1.07
     effluents
    0.89
    ،
    0.88
     of
    0.88
    2
    0.83
     Cenomanian
    0.82
    fords
    0.82
     evidences
    0.81
     autres
    0.80
    ।
    0.80
    Activations Density 0.000%

    No Known Activations