© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207209
    Prev
    Next
    INDEX
    Explanations

    say ","

    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_56_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
     или
    1.29
    或
    1.27
    หรือ
    1.22
     or
    1.16
     அல்லது
    1.13
     hoặc
    1.12
     또는
    1.11
     ಅಥವಾ
    1.11
     અથવા
    1.10
     atau
    1.05
    POSITIVE LOGITS
     Neither
    0.54
    /
    0.49
     вместе
    0.49
     együtt
    0.46
    一緒に
    0.45
     neither
    0.45
     along
    0.44
     împre
    0.43
     beraber
    0.43
     Along
    0.42
    Activations Density 0.011%

    No Known Activations