© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9072
    Prev
    Next
    INDEX
    Explanations

    certainty and likelihood

    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_13_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
     S
    0.22
     համար
    0.21
     सावधानी
    0.21
     lineColorSpace
    0.20
     attentively
    0.20
    Ｓ
    0.20
    Ꮅ
    0.20
     ସ
    0.20
    ్‌
    0.19
     clump
    0.19
    POSITIVE LOGITS
    ال
    0.25
    주
    0.24
    ou
    0.23
     errado
    0.23
    no
    0.23
     wont
    0.23
    controller
    0.23
     hilar
    0.23
     nordic
    0.22
     presencia
    0.22
    Activations Density 0.081%

    No Known Activations