© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102471
    Prev
    Next
    INDEX
    Explanations

    faces, holdings, guest

    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_14_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
    VICIO
    0.56
    c
    0.55
     terapia
    0.51
     hielo
    0.51
     scallops
    0.51
    くちゃ
    0.51
    ETER
    0.49
     scallop
    0.49
    ariance
    0.49
    жие
    0.48
    POSITIVE LOGITS
    硃
    0.61
     محس
    0.61
    厡
    0.59
    <unused1059>
    0.59
     de
    0.59
     สำหรับ
    0.58
     อาจ
    0.58
     Букмекердик
    0.58
     Букмекерлер
    0.56
     మీకు
    0.55
    Activations Density 0.024%

    No Known Activations