© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20476
    Prev
    Next
    INDEX
    Explanations

    tell me about

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     capturedPlayer
    0.48
    𒐪
    0.47
    <unused2121>
    0.44
    <unused2117>
    0.43
     capas
    0.42
     tagReport
    0.41
    тьяна
    0.41
    <unused2183>
    0.41
    <unused2125>
    0.40
    <unused2126>
    0.40
    POSITIVE LOGITS
     Fort
    0.47
     Drosophila
    0.47
     Kanji
    0.46
     Bhag
    0.45
     pesantren
    0.45
     Delhi
    0.45
     Ayurveda
    0.44
     Praia
    0.43
     annuities
    0.42
     Himalayan
    0.41
    Activations Density 0.025%

    No Known Activations