© 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. 86209
    Prev
    Next
    INDEX
    Explanations

    Billie Eilish

    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
     on
    0.66
    دين
    0.65
     This
    0.64
     killing
    0.63
    Résumé
    0.63
    า
    0.63
     kill
    0.62
    OT
    0.61
     It
    0.59
    строй
    0.59
    POSITIVE LOGITS
     you
    0.69
     Ј
    0.66
    γ
    0.65
    homes
    0.64
    jew
    0.63
    inity
    0.62
    zing
    0.61
    ანს
    0.61
    ٹ
    0.61
    }}$,
    0.59
    Activations Density 0.002%

    No Known Activations