© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234196
    Prev
    Next
    INDEX
    Explanations

    API endpoints and database statements

    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_32_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
    𝓌
    0.43
    র্ধ
    0.40
    getVersion
    0.40
     MDLVertex
    0.37
    衣装
    0.37
     clone
    0.36
    augment
    0.36
     öğrenciler
    0.36
    鷺
    0.36
    HDR
    0.36
    POSITIVE LOGITS
     Matches
    0.40
     Simple
    0.38
    PutMapping
    0.37
     geste
    0.36
     abandoned
    0.36
     Owner
    0.36
    irne
    0.36
     Example
    0.34
     transc
    0.34
     후
    0.34
    Activations Density 0.001%

    No Known Activations