© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14375
    Prev
    Next
    INDEX
    Explanations

    6 related terms

    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_13_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
     Labrenzia
    0.39
     යුතු
    0.37
    粆
    0.37
    茈
    0.37
    肨
    0.37
     milliliters
    0.37
     कॉल्ड
    0.37
    畴
    0.37
     Brenner
    0.36
    ĵo
    0.36
    POSITIVE LOGITS
    at
    0.49
    er
    0.47
    eren
    0.44
     laund
    0.43
    one
    0.42
    played
    0.42
    Neil
    0.41
    жі
    0.41
    al
    0.41
    TV
    0.41
    Activations Density 0.026%

    No Known Activations