© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54148
    Prev
    Next
    INDEX
    Explanations

    HTML forms and vue components

    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_30_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
    <unused336>
    0.37
     benöt
    0.37
    করিয়
    0.36
     już
    0.35
     अंजीर
    0.35
    ➩
    0.35
    üllt
    0.35
    filling
    0.35
     wɔ
    0.35
    ᴙ
    0.34
    POSITIVE LOGITS
    modal
    0.43
    Modal
    0.39
     modal
    0.37
    fac
    0.37
     Hey
    0.37
     Back
    0.37
     Fac
    0.35
     modalities
    0.35
     Models
    0.35
     Modal
    0.35
    Activations Density 0.000%

    No Known Activations