© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210572
    Prev
    Next
    INDEX
    Explanations

    90%

    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_5_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
    ת
    1.38
    ↵
    1.37
    ले
    1.37
    “
    1.34
    ต
    1.33
    5
    1.31
    "
    1.26
    ن
    1.26
    你
    1.24
    С
    1.23
    POSITIVE LOGITS
    j
    1.53
    ip
    1.21
    u
    1.20
    have
    1.17
    to
    1.16
    وں
    1.13
    1.10
    ij
    1.09
    ong
    1.09
    il
    1.05
    Activations Density 0.012%

    No Known Activations