© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232675
    Prev
    Next
    INDEX
    Explanations

    compared to

    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_32_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
     رأس
    0.36
     τόσο
    0.36
    another
    0.35
    created
    0.34
     created
    0.33
     eş
    0.33
     Ă
    0.33
     m
    0.33
    Marina
    0.33
     Nik
    0.32
    POSITIVE LOGITS
     invece
    0.45
     rağmen
    0.44
     вместо
    0.44
     thì
    0.40
    相比
    0.39
     Existing
    0.39
     zusammen
    0.39
     વિદ્ય
    0.38
    价比
    0.38
    ோவில்
    0.37
    Activations Density 0.001%

    No Known Activations