© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82630
    Prev
    Next
    INDEX
    Explanations

    visited places or times

    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
    ี
    1.38
    ٦
    1.33
    ى
    1.27
    ным
    1.21
    𝐧
    1.20
    ן
    1.12
    ல்
    1.11
    𝐝
    1.11
    р
    1.10
     tràn
    1.09
    POSITIVE LOGITS
    '
    2.02
    ای
    1.67
    א
    1.59
    able
    1.48
    का
    1.47
    and
    1.46
    ک
    1.38
    inin
    1.35
    i
    1.34
    ए
    1.34
    Activations Density 0.001%

    No Known Activations