© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57127
    Prev
    Next
    INDEX
    Explanations

    common german 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_11_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
    customer
    0.63
    but
    0.62
    could
    0.61
    ો
    0.61
     possibilidade
    0.61
    *
    0.59
    can
    0.58
    Можно
    0.58
    5
    0.56
    2
    0.55
    POSITIVE LOGITS
     petroleum
    0.58
    ר
    0.56
     aides
    0.55
    ರೇ
    0.54
     throm
    0.53
     ucc
    0.53
     nhiệm
    0.52
    р
    0.51
     steaming
    0.51
    뢨
    0.51
    Activations Density 0.015%

    No Known Activations