© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149883
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-English words

    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_23_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
    ਤੇ
    0.41
    ਤ
    0.41
    voor
    0.38
    its
    0.38
    hets
    0.38
     remover
    0.37
    క
    0.37
    lech
    0.37
     informed
    0.37
    ಸ
    0.36
    POSITIVE LOGITS
     насы
    0.46
     био
    0.45
     ρ
    0.43
     চালা
    0.42
     回転
    0.42
     ɛ
    0.42
    dsc
    0.42
     аса
    0.42
     আট
    0.42
     なかっ
    0.42
    Activations Density 0.000%

    No Known Activations