© 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. 112714
    Prev
    Next
    INDEX
    Explanations

    ade / ada variations

    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
    к
    1.27
    تين
    1.17
    ת
    1.11
    ק
    1.11
    .
    1.09
    (
    0.98
    <0x80>
    0.97
    er
    0.96
    т
    0.93
    c
    0.93
    POSITIVE LOGITS
    1.49
     è
    1.09
    この
    1.08
    の
    1.07
     จ
    1.05
     โดย
    1.05
     इस
    1.02
     resulta
    1.02
    ことを
    1.01
     บ
    1.00
    Activations Density 0.000%

    No Known Activations