© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155451
    Prev
    Next
    INDEX
    Explanations

    Gin

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    So
    0.43
    ágina
    0.40
    მ
    0.38
    บล
    0.38
    ГА
    0.38
     была
    0.37
    Simplify
    0.37
     SIMPLE
    0.36
     бы
    0.35
     ។
    0.35
    POSITIVE LOGITS
    cj
    0.59
    cF
    0.58
    cil
    0.55
    cami
    0.53
    cD
    0.52
    categorias
    0.51
    cimiento
    0.50
    cw
    0.50
    cC
    0.48
    cara
    0.48
    Activations Density 0.000%

    No Known Activations