© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151571
    Prev
    Next
    INDEX
    Explanations

    many reasons, things, ways

    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_23_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
     establece
    0.36
    祕
    0.33
    reff
    0.33
    pac
    0.32
     საქ
    0.32
    erex
    0.32
    future
    0.32
    conex
    0.32
    sean
    0.31
    }+(
    0.31
    POSITIVE LOGITS
     различ
    0.37
     때
    0.35
    రుగు
    0.35
    тельной
    0.35
     Different
    0.34
     variously
    0.34
     variado
    0.34
     อาจ
    0.34
     derive
    0.33
     Христо
    0.32
    Activations Density 0.022%

    No Known Activations