© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178092
    Prev
    Next
    INDEX
    Explanations

    you can copy and paste anywhere

    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_29_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
     உதார
    0.38
     Cæ
    0.38
     mydb
    0.38
    🍞
    0.37
     intArray
    0.37
     commandBuffer
    0.37
     croc
    0.37
     برم
    0.36
    蟒
    0.36
     интегра
    0.36
    POSITIVE LOGITS
    except
    0.51
     except
    0.48
    Koh
    0.46
    Gan
    0.46
     because
    0.42
    Karena
    0.42
    Because
    0.41
    Ron
    0.41
    Như
    0.41
    ali
    0.41
    Activations Density 0.000%

    No Known Activations