© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216610
    Prev
    Next
    INDEX
    Explanations

    repeated structure or phrase

    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_31_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
     tâm
    0.35
     bedside
    0.34
    invocation
    0.33
     گم
    0.32
    Interpretation
    0.32
     я
    0.32
     mess
    0.32
     뭐
    0.32
     넘
    0.32
     염
    0.32
    POSITIVE LOGITS
    िलास
    0.43
    uruh
    0.41
     रोका
    0.40
     Preventing
    0.40
    uhà
    0.38
     mencegah
    0.38
     preventing
    0.37
     ハ
    0.37
     viktigt
    0.37
     Equally
    0.36
    Activations Density 0.000%

    No Known Activations