© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 166778
    Prev
    Next
    INDEX
    Explanations

    Gavrilo Princip/Wav2Lip

    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
    erweise
    0.49
    нга
    0.46
    enangan
    0.41
    onbury
    0.39
    ynd
    0.38
    olet
    0.37
    േക്ക്
    0.35
    ే
    0.35
    okeh
    0.34
    त्न
    0.34
    POSITIVE LOGITS
    ्ह
    0.51
    s
    0.49
    ્સ
    0.41
    ska
    0.41
    களில்
    0.40
    sla
    0.40
    ের
    0.39
    soci
    0.39
    ez
    0.38
    ਆਂ
    0.38
    Activations Density 0.000%

    No Known Activations