© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198523
    Prev
    Next
    INDEX
    Explanations

    babylonia, babymetal, baby names

    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_4_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
    적으로
    0.75
    ového
    0.75
    OF
    0.68
    obo
    0.68
    ード
    0.66
    砰
    0.65
    нка
    0.65
    0.64
    omás
    0.64
    어졌
    0.64
    POSITIVE LOGITS
    ↵
    1.45
    ir
    1.27
    5
    1.23
    baby
    1.20
     baby
    1.18
    1
    1.17
    و
    1.16
    3
    1.07
    4
    1.05
    ل
    1.05
    Activations Density 0.001%

    No Known Activations