© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60299
    Prev
    Next
    INDEX
    Explanations

    emerges

    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
    >
    1.23
    ৫
    1.12
    ad
    1.00
     be
    0.93
    ach
    0.93
    高
    0.93
    స్‌
    0.89
    (
    0.89
    ig
    0.86
     prioritize
    0.82
    POSITIVE LOGITS
    ί
    1.44
    си
    1.33
    то
    1.32
    с
    1.32
    1
    1.30
    ма
    1.21
    ล
    1.20
    на
    1.19
    re
    1.13
    ре
    1.10
    Activations Density 0.000%

    No Known Activations