© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138260
    Prev
    Next
    INDEX
    Explanations

    game show host

    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_12_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
     aspects
    0.61
     Aspects
    0.58
    sha
    0.56
    ná
    0.54
     offence
    0.53
     Kamil
    0.52
    nisse
    0.52
    )->
    0.51
     Jawa
    0.51
     Origins
    0.50
    POSITIVE LOGITS
     แต่
    0.60
     selon
    0.57
     шокола
    0.55
    番組
    0.54
     برنام
    0.52
     پرت
    0.50
     lot
    0.50
    ıt
    0.50
     সম্পদের
    0.50
    itochond
    0.49
    Activations Density 0.002%

    No Known Activations