© 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. 123067
    Prev
    Next
    INDEX
    Explanations

    Komoot, Komonews, Komsomol, Arnold, komod

    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
    ется
    0.87
     It
    0.66
    ],
    0.65
    ции
    0.65
    is
    0.63
    ension
    0.63
    л
    0.61
    жно
    0.59
    ви
    0.59
    of
    0.58
    POSITIVE LOGITS
     itinéraires
    0.71
     apparaissent
    0.68
    Վ
    0.68
     creciente
    0.67
     futuras
    0.66
     madam
    0.66
    Ս
    0.66
     Bernadette
    0.65
     hectares
    0.65
     ordinateur
    0.65
    Activations Density 0.000%

    No Known Activations