© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86230
    Prev
    Next
    INDEX
    Explanations

    blameless postmortems, Bleichenbacher's, Bloomsdale, Blavatsky

    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_3_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
    ai
    0.63
    <unused2140>
    0.63
    欤
    0.60
    ারের
    0.60
    ern
    0.59
    INGER
    0.59
    }"/>
    0.59
    <unused2113>
    0.59
    assapi
    0.58
     poche
    0.58
    POSITIVE LOGITS
    i
    0.85
    י
    0.78
    ↵↵
    0.72
    C
    0.71
    ↵↵↵
    0.67
    Owin
    0.65
    シ
    0.65
    start
    0.64
    this
    0.62
    startsWith
    0.62
    Activations Density 0.000%

    No Known Activations