© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225389
    Prev
    Next
    INDEX
    Explanations

    full human detail

    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_10_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
     –
    0.22
    স
    0.21
    Є
    0.21
     curator
    0.20
     of
    0.20
     pastor
    0.20
     from
    0.20
     not
    0.19
    วัสดี
    0.19
     '-'
    0.19
    POSITIVE LOGITS
    la
    0.29
    and
    0.29
    8
    0.29
     clase
    0.28
     scorsa
    0.27
     specifica
    0.27
    ၉
    0.27
    sh
    0.27
    ların
    0.26
    arın
    0.26
    Activations Density 0.003%

    No Known Activations