© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80106
    Prev
    Next
    INDEX
    Explanations

    Observatory

    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_0_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
    in
    1.47
    is
    1.38
    n
    1.29
    da
    1.25
    an
    1.16
    zied
    1.16
    was
    1.16
    ン
    1.16
    cción
    1.15
    inę
    1.13
    POSITIVE LOGITS
    ח
    1.85
     that
    1.70
    ä
    1.59
     automóviles
    1.48
    то
    1.48
    ור
    1.48
     jugadores
    1.46
     ambientales
    1.46
    ני
    1.45
     acuerdos
    1.45
    Activations Density 0.000%

    No Known Activations