© 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. 31457
    Prev
    Next
    INDEX
    Explanations

    And followed by transition word

    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
    閻
    0.36
    国道
    0.36
    So
    0.35
    ர்களையும்
    0.35
    Frequent
    0.35
     estacion
    0.34
    用地
    0.34
     potholes
    0.34
    阎
    0.33
    exper
    0.33
    POSITIVE LOGITS
     продолжа
    0.45
     continue
    0.42
    ल्लाला
    0.40
     dalej
    0.39
     계속
    0.39
     হারিয়ে
    0.38
    続ける
    0.38
     продовжу
    0.37
     continues
    0.37
    కుండా
    0.37
    Activations Density 0.001%

    No Known Activations