© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197547
    Prev
    Next
    INDEX
    Explanations

    'words' or specific phrases in quotes

    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_9_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
    。
    0.65
     can
    0.64
    ה
    0.57
     has
    0.55
    a
    0.55
    。",
    0.53
    ，
    0.53
    ه
    0.52
     was
    0.51
    ،
    0.48
    POSITIVE LOGITS
    ים
    0.55
    ের
    0.54
    s
    0.53
    وں
    0.52
    ی
    0.51
    স
    0.45
    𝘴
    0.44
    да
    0.43
    𝐬
    0.43
    ات
    0.43
    Activations Density 0.019%

    No Known Activations