© 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. 51192
    Prev
    Next
    INDEX
    Explanations

    height and mountains

    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
     fabricate
    0.19
    ות
    0.18
     Афри
    0.17
    {
    0.17
     ሴ
    0.17
    {}'.
    0.17
     않는
    0.16
     ので
    0.16
     {}'.
    0.16
     permanec
    0.16
    POSITIVE LOGITS
    on
    0.29
    us
    0.26
    and
    0.25
    ru
    0.24
    ig
    0.24
    to
    0.24
    hi
    0.23
    is
    0.23
    uk
    0.23
    time
    0.23
    Activations Density 0.017%

    No Known Activations