© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9904
    Prev
    Next
    INDEX
    Explanations

    sandboxing environments

    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_13_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
    u
    0.17
     নভেম্বর
    0.16
    noun
    0.15
    conce
    0.15
    an
    0.14
    odore
    0.14
    atino
    0.14
    メータ
    0.14
    তাহাকে
    0.14
    梧
    0.14
    POSITIVE LOGITS
    À
    0.20
     and
    0.17
    .”—
    0.16
     cantar
    0.16
     are
    0.16
     wealth
    0.16
     für
    0.16
    ⟣
    0.16
    WL
    0.16
     pärast
    0.16
    Activations Density 0.007%

    No Known Activations