© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175178
    Prev
    Next
    INDEX
    Explanations

    rooms and spaces

    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_24_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
     চলেছে
    0.38
    Ru
    0.36
    (
    0.36
     IPS
    0.34
    Marsh
    0.34
    Countryside
    0.33
    Herm
    0.33
    Hall
    0.33
     Wak
    0.33
     दोषियों
    0.33
    POSITIVE LOGITS
     pouls
    0.44
     meia
    0.40
    音声
    0.39
    壹
    0.38
     pulse
    0.37
     frisch
    0.37
     pulsing
    0.36
     puls
    0.36
    藏
    0.36
     simbolo
    0.36
    Activations Density 0.000%

    No Known Activations