© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7971
    Prev
    Next
    INDEX
    Explanations

    musical titles and authors

    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_40_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
    FindFileData
    0.40
    finden
    0.37
    dans
    0.36
    echen
    0.35
     इमरजेंसी
    0.35
    .>
    0.35
     auctor
    0.35
     گرد
    0.35
    BUL
    0.35
    beiter
    0.34
    POSITIVE LOGITS
     ringan
    0.42
    ڙ
    0.41
     badge
    0.41
     yearn
    0.37
    輕
    0.37
    埋
    0.37
     yearning
    0.36
    perman
    0.36
     ľ
    0.36
    漂亮
    0.36
    Activations Density 0.018%

    No Known Activations