© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157554
    Prev
    Next
    INDEX
    Explanations

    det + word suffix

    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_2_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
    ਾ
    1.28
    م
    1.26
    ри
    1.23
    ر
    1.23
    ம்
    1.21
    '
    1.17
    ará
    1.16
    üste
    1.16
    ie
    1.11
    ை
    1.10
    POSITIVE LOGITS
    the
    1.04
    मारा
    0.88
     it
    0.88
    ष्मान
    0.87
     an
    0.86
    ma
    0.85
     mengaku
    0.85
    ш
    0.85
    who
    0.84
     kwamba
    0.82
    Activations Density 0.000%

    No Known Activations