© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176827
    Prev
    Next
    INDEX
    Explanations

    return true

    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_24_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
     inspection
    0.43
     inspect
    0.42
     detection
    0.42
     inspe
    0.40
    て
    0.40
    意
    0.40
     সংঘ
    0.39
    ଛ
    0.38
    Ꮸ
    0.38
    amet
    0.38
    POSITIVE LOGITS
     Ио
    0.42
     lan
    0.41
     Venice
    0.41
     roasted
    0.39
     Khar
    0.39
     Firenze
    0.39
     leider
    0.38
     Fiore
    0.38
     filmed
    0.37
     Ё
    0.37
    Activations Density 0.001%

    No Known Activations