© 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. 215863
    Prev
    Next
    INDEX
    Explanations

    model.rf, .ggml, .gguf, .ot, .mcfunction

    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
     lower
    0.38
    çük
    0.37
     nég
    0.37
     tuv
    0.36
     even
    0.36
     |=
    0.36
     grilling
    0.35
    uq
    0.35
    /
    0.35
     posse
    0.35
    POSITIVE LOGITS
    ждествен
    0.39
     забу
    0.38
    tras
    0.37
     पृष्ठ
    0.36
    rules
    0.36
     συνο
    0.35
     हिमा
    0.35
    Buttons
    0.35
    ések
    0.35
    imura
    0.34
    Activations Density 0.002%

    No Known Activations