© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195544
    Prev
    Next
    INDEX
    Explanations

    time and consideration

    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_26_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
     để
    0.37
     (-)
    0.36
    td
    0.36
    Od
    0.36
    }
    0.36
     beginners
    0.35
    cue
    0.35
    Swe
    0.34
    ாலே
    0.34
    to
    0.34
    POSITIVE LOGITS
     nostra
    0.45
     nomor
    0.44
     zeker
    0.43
     perfeita
    0.43
     transacción
    0.42
     nostro
    0.42
     kucing
    0.41
    哚
    0.41
     exceptionnelle
    0.40
     opravdu
    0.40
    Activations Density 0.001%

    No Known Activations