© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31331
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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_50_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
     mö
    0.38
    男孩
    0.37
     गिरि
    0.36
    মুর
    0.36
     ብ
    0.36
    壬
    0.35
     MER
    0.35
     Exposed
    0.35
     garage
    0.35
     krist
    0.35
    POSITIVE LOGITS
    absValue
    0.40
     Jü
    0.39
    祸
    0.38
    rayon
    0.38
    joni
    0.38
    INUS
    0.38
    glycer
    0.38
    jgl
    0.38
    ジュール
    0.37
    ary
    0.37
    Activations Density 0.000%

    No Known Activations