© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204282
    Prev
    Next
    INDEX
    Explanations

    ached, aching

    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_6_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
    \
    0.89
    AN
    0.87
    Suppose
    0.85
    你有
    0.84
    There
    0.84
     quell
    0.83
    스
    0.81
    You
    0.80
     potencial
    0.80
    INE
    0.78
    POSITIVE LOGITS
    k
    1.34
    l
    1.33
    ur
    1.30
    v
    1.30
    h
    1.17
    ik
    1.15
    og
    1.13
    ного
    1.10
    kort
    1.09
    ed
    1.08
    Activations Density 0.000%

    No Known Activations