© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253584
    Prev
    Next
    INDEX
    Explanations

    consistency

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    cursos
    0.39
     utilizzando
    0.37
    wege
    0.37
     utilizando
    0.35
     –
    0.35
     pools
    0.35
    rope
    0.35
    pools
    0.35
     experiencia
    0.34
    ဤ
    0.34
    POSITIVE LOGITS
     consistent
    0.88
     Consistent
    0.74
    Consistent
    0.70
    consistent
    0.68
     consistente
    0.46
    一致
    0.42
     Consistency
    0.41
     hosted
    0.39
     Shared
    0.39
     where
    0.38
    Activations Density 0.003%

    No Known Activations