© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42235
    Prev
    Next
    INDEX
    Explanations

    regular polygons and equilateral triangles

    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_22_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
     idha
    0.25
    ecycle
    0.23
     chimneys
    0.23
     parecen
    0.22
     bootstra
    0.22
     compartido
    0.21
     percep
    0.21
    㚣
    0.21
     Ansible
    0.21
     adresu
    0.21
    POSITIVE LOGITS
     According
    0.22
    According
    0.21
     Result
    0.20
     subparagraph
    0.19
     Berber
    0.19
    Specific
    0.19
     Gallagher
    0.19
    Ã
    0.19
    ):
    0.19
     दु
    0.18
    Activations Density 0.002%

    No Known Activations