© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40919
    Prev
    Next
    INDEX
    Explanations

    propolis, propylene glycol, density

    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_3_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
     on
    1.09
    ation
    0.72
    ong
    0.71
    ↵
    0.70
    ens
    0.70
    lt
    0.66
    si
    0.65
    land
    0.65
    ain
    0.64
     ऑन
    0.64
    POSITIVE LOGITS
     propel
    0.91
    i
    0.91
    ك
    0.91
    ي
    0.86
     boreal
    0.77
    ۳
    0.75
     Fabrizio
    0.74
     predisposition
    0.73
    يين
    0.73
     Talon
    0.71
    Activations Density 0.009%

    No Known Activations