© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200688
    Prev
    Next
    INDEX
    Explanations

    questions starting with "how"

    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_12_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
    bury
    0.40
    d
    0.35
    an
    0.33
    bow
    0.33
    land
    0.32
    r
    0.32
    have
    0.32
    bird
    0.32
    apsingToolbar
    0.32
    brightness
    0.32
    POSITIVE LOGITS
    1
    0.43
     Rates
    0.42
    3
    0.40
     Cros
    0.40
     Tunis
    0.39
     Bayern
    0.39
     Dari
    0.39
     Supported
    0.39
     Puoi
    0.39
     Rice
    0.39
    Activations Density 0.001%

    No Known Activations