© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195948
    Prev
    Next
    INDEX
    Explanations

    letter 'a' followed by punctuation

    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_27_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
    MTAB
    0.42
    द्वानी
    0.40
     gewisse
    0.39
    খান
    0.38
    олові
    0.37
    しかし
    0.37
    ベント
    0.37
    哚
    0.37
    𝗚
    0.37
    इंडिया
    0.36
    POSITIVE LOGITS
    othy
    0.36
     Ent
    0.36
     Lane
    0.35
     inventory
    0.35
     metr
    0.35
     ph
    0.35
     precisam
    0.35
     gerekiyor
    0.35
    emic
    0.34
    utzen
    0.34
    Activations Density 0.001%

    No Known Activations