© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261102
    Prev
    Next
    INDEX
    Explanations

    common for

    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_22_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
     conceivably
    0.42
    ——
    0.41
     उपलब्ध
    0.40
    Communications
    0.40
     actually
    0.38
     :
    0.38
     faktisk
    0.38
     Presumably
    0.38
     notably
    0.37
    ivative
    0.37
    POSITIVE LOGITS
    asyarakat
    0.51
     табу
    0.44
    agility
    0.42
     කළ
    0.42
    𝘩
    0.42
     လက်
    0.41
     პროფილი
    0.41
     агре
    0.40
    ならでは
    0.40
    BufOffset
    0.40
    Activations Density 0.006%

    No Known Activations