© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132095
    Prev
    Next
    INDEX
    Explanations

    Russian suffixes, Korean syllables, or single letters

    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_1_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
    .
    1.71
    ların
    1.16
    ts
    1.15
    ta
    1.13
    та
    1.09
    ק
    1.05
     a
    1.03
    á
    1.02
    .</
    0.97
    UM
    0.96
    POSITIVE LOGITS
    ه
    1.50
    د
    1.40
    는
    1.34
    ਰ
    1.34
    extrait
    1.22
    は
    1.20
    जवळ
    1.13
    간
    1.13
    a
    1.12
    ب
    1.10
    Activations Density 0.000%

    No Known Activations