© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110306
    Prev
    Next
    INDEX
    Explanations

    Eleanor Vance

    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
    f
    1.66
    <0x80>
    1.50
    v
    1.46
    '
    1.41
    y
    1.36
    I
    1.27
    س
    1.22
    .
    1.15
    h
    1.10
    <0x86>
    1.09
    POSITIVE LOGITS
    ৮
    1.63
    ৬
    1.54
    ون
    1.52
    א
    1.49
    ৯
    1.47
     on
    1.38
    ৪
    1.27
    на
    1.27
    ת
    1.26
    ৭
    1.23
    Activations Density 0.000%

    No Known Activations