© 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. 152963
    Prev
    Next
    INDEX
    Explanations

    beyond that

    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
     poet
    0.47
    毕竟
    0.38
    )_{
    0.38
    𝒆
    0.38
     mixtape
    0.36
     поэ
    0.36
    কর
    0.35
    )|\
    0.35
     գ
    0.34
     suất
    0.34
    POSITIVE LOGITS
     separado
    0.39
    oleans
    0.38
     namanya
    0.37
     distances
    0.36
     expl
    0.36
     angeles
    0.36
     dijo
    0.35
    터를
    0.35
     uveden
    0.35
     Се
    0.35
    Activations Density 0.000%

    No Known Activations