© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36669
    Prev
    Next
    INDEX
    Explanations

    cracks and fences

    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_11_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
    ključ
    0.27
     suivie
    0.23
    响起
    0.22
    strncpy
    0.22
    悴
    0.22
     weaken
    0.22
     réforme
    0.22
    vär
    0.22
     preocupa
    0.21
     copier
    0.21
    POSITIVE LOGITS
    βά
    0.22
    Apart
    0.21
    েলে
    0.21
     NITRO
    0.20
    ip
    0.20
    ो
    0.20
    𝘳
    0.19
     கிட்டத்தட்ட
    0.19
     لئے
    0.19
    λα
    0.19
    Activations Density 0.016%

    No Known Activations