© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215048
    Prev
    Next
    INDEX
    Explanations

    Milvus

    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_5_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
    ong
    1.63
    im
    1.41
    in
    1.36
    д
    1.34
    an
    1.34
    p
    1.26
    ies
    1.20
    ip
    1.20
    ia
    1.14
    ua
    1.13
    POSITIVE LOGITS
     formular
    1.21
     destac
    1.16
     protégé
    1.13
    ת
    1.11
     recib
    1.10
     proteg
    1.10
     véritable
    1.09
     bloquear
    1.09
    Ҷ
    1.09
     relacion
    1.07
    Activations Density 0.000%

    No Known Activations