© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143305
    Prev
    Next
    INDEX
    Explanations

    positive

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ನನ್ನು
    0.43
     облі
    0.38
     bench
    0.38
    Reducing
    0.38
    乏
    0.37
     ساری
    0.37
    Corre
    0.37
    扳
    0.37
    လေ
    0.36
    深く
    0.36
    POSITIVE LOGITS
     positive
    0.53
     Positive
    0.48
     material
    0.47
     positivas
    0.47
     materially
    0.45
     positif
    0.44
    material
    0.43
    positive
    0.42
     положи
    0.40
     positifs
    0.40
    Activations Density 0.004%

    No Known Activations