© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259985
    Prev
    Next
    INDEX
    Explanations

    first-party cookies

    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_22_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
    інки
    0.42
    Espagne
    0.42
    を行い
    0.40
    اسم
    0.39
    ヴィ
    0.39
    ôté
    0.39
    ₎
    0.39
    ην
    0.38
    essai
    0.38
    Don
    0.38
    POSITIVE LOGITS
    пей
    0.54
     recurso
    0.49
     facades
    0.49
     அல்ல
    0.48
     нужда
    0.48
     railings
    0.46
    itamos
    0.45
     않
    0.45
     culprits
    0.44
     కూ
    0.44
    Activations Density 0.000%

    No Known Activations