© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89919
    Prev
    Next
    INDEX
    Explanations

    Detecting when a prompt starts a title

    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_11_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
    \
    0.66
    เขา
    0.60
    техни
    0.59
    ي
    0.59
    </em>
    0.56
    ه
    0.56
    들이
    0.55
    Игра
    0.55
    (
    0.55
    </strong>
    0.54
    POSITIVE LOGITS
    gris
    0.64
    nis
    0.63
     ሕ
    0.63
     analges
    0.61
     inactivació
    0.61
     insuffis
    0.60
     በፍ
    0.60
     invincible
    0.59
     plufieurs
    0.58
     灬
    0.58
    Activations Density 0.002%

    No Known Activations