© 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. 42414
    Prev
    Next
    INDEX
    Explanations

    technical aspects

    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
    A
    0.65
     on
    0.52
    B
    0.52
    S
    0.52
    T
    0.48
    C
    0.48
    "
    0.48
    The
    0.47
    ون
    0.45
     locating
    0.45
    POSITIVE LOGITS
    礡
    0.54
     miteinander
    0.51
     solche
    0.51
    фі
    0.50
     tasa
    0.50
     Diskussion
    0.50
     dobbiamo
    0.50
     Veranstaltungen
    0.48
     enjeux
    0.48
     mnog
    0.48
    Activations Density 0.000%

    No Known Activations