© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42468
    Prev
    Next
    INDEX
    Explanations

    return value

    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
    Transitions
    0.45
     सफलतापूर्वक
    0.42
     Metals
    0.40
     Transitions
    0.38
     Nox
    0.38
    compensation
    0.38
    transitions
    0.37
     ½
    0.37
     transitional
    0.37
    canceled
    0.37
    POSITIVE LOGITS
     amicable
    0.44
    Kami
    0.41
    があります
    0.41
    kami
    0.41
    ガネ
    0.40
    胥
    0.39
     psychology
    0.38
    낍
    0.38
    ait
    0.38
     appre
    0.38
    Activations Density 0.002%

    No Known Activations