© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215787
    Prev
    Next
    INDEX
    Explanations

    compatibility issues

    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_31_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
    ใ
    0.41
    )];
    0.38
     porridge
    0.38
     voie
    0.38
    =")
    0.37
    Loads
    0.37
     clover
    0.36
     booze
    0.35
     ყველა
    0.35
    )}+\
    0.35
    POSITIVE LOGITS
     compatible
    0.39
     compatibles
    0.39
     Marion
    0.37
     Compatible
    0.37
    驩
    0.37
     kompat
    0.36
     Nawab
    0.36
    Marion
    0.36
    替换
    0.36
     совмести
    0.36
    Activations Density 0.004%

    No Known Activations