© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144709
    Prev
    Next
    INDEX
    Explanations

    Abusive, abundant, abduction, abstain, yam

    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_0_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
    า
    2.28
    an
    2.22
    ла
    2.11
    a
    2.11
    ти
    1.91
    ي
    1.80
    ס
    1.63
    اك
    1.60
    )
    1.60
    as
    1.55
    POSITIVE LOGITS
    ため
    1.27
    ために
    1.24
    ьте
    1.24
    Active
    1.16
     are
    1.14
    ায়
    1.14
    し
    1.13
    Width
    1.12
    ImageUrl
    1.12
     végétale
    1.10
    Activations Density 0.001%

    No Known Activations