© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205101
    Prev
    Next
    INDEX
    Explanations

    not left unattended

    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
     unattended
    1.11
     Nietzsche
    0.70
     Niet
    0.39
     unsupervised
    0.38
    浮
    0.38
    चुरल
    0.37
     Policies
    0.37
    umbo
    0.36
    yship
    0.36
    ossed
    0.36
    POSITIVE LOGITS
     herd
    0.46
     dés
    0.43
     Herd
    0.38
    agang
    0.38
    ohon
    0.38
     foreground
    0.37
    稟
    0.37
     déc
    0.36
     lanceol
    0.36
     unt
    0.35
    Activations Density 0.004%

    No Known Activations