© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13930
    Prev
    Next
    INDEX
    Explanations

    seating preferences, area, class

    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_13_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
     પરંતુ
    0.57
    }}}=
    0.54
    цах
    0.52
    mittag
    0.52
    ндар
    0.51
    🤱
    0.50
     maxn
    0.48
    трен
    0.47
    फलता
    0.47
    మయ్య
    0.47
    POSITIVE LOGITS
    0
    0.83
    1
    0.66
    5
    0.65
    3
    0.63
    9
    0.62
    6
    0.59
    2
    0.57
    has
    0.55
    The
    0.51
    4
    0.51
    Activations Density 0.004%

    No Known Activations