© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78900
    Prev
    Next
    INDEX
    Explanations

    designated, selected, special

    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_29_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
    ﷻ
    0.38
    âng
    0.35
    むしろ
    0.34
    finity
    0.34
    argu
    0.34
    যোগ
    0.33
     streets
    0.32
    憶
    0.32
    수로
    0.32
    imm
    0.32
    POSITIVE LOGITS
     determinadas
    0.48
     designated
    0.44
     spezielle
    0.42
     determinada
    0.41
     selected
    0.41
     bepaalde
    0.41
    有两种
    0.41
     tertentu
    0.40
     ख़ास
    0.40
     مخصوص
    0.39
    Activations Density 0.015%

    No Known Activations