© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217759
    Prev
    Next
    INDEX
    Explanations

    your favorite

    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_16_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
    MAPb
    0.58
     Chayin
    0.55
    멩
    0.55
    얗
    0.54
    䪲
    0.54
     deň
    0.52
    <unused654>
    0.52
    notlocked
    0.52
    starcore
    0.51
     なり
    0.51
    POSITIVE LOGITS
     P
    0.63
     switches
    0.57
     S
    0.54
     can
    0.52
     L
    0.51
     A
    0.50
     the
    0.50
    ک
    0.49
    Case
    0.49
     disconnection
    0.48
    Activations Density 0.000%

    No Known Activations