© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79646
    Prev
    Next
    INDEX
    Explanations

    uninhibited spree

    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_0_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
     can
    1.87
    n
    1.56
    ၁
    1.49
    ють
    1.47
    ο
    1.47
     cambi
    1.43
    am
    1.42
    ある
    1.32
     escrib
    1.32
    ری
    1.30
    POSITIVE LOGITS
    ER
    1.44
    AT
    1.35
    ح
    1.23
     మరియు
    1.21
    ر
    1.21
    ção
    1.20
    na
    1.16
    rieben
    1.13
    für
    1.11
    ne
    1.10
    Activations Density 0.000%

    No Known Activations