© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80673
    Prev
    Next
    INDEX
    Explanations

    Italian words

    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_53_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
    Bark
    0.43
     bark
    0.42
     sol
    0.41
     Bark
    0.40
     Aleg
    0.39
     yat
    0.38
     Ecc
    0.36
    酊
    0.36
     Barker
    0.36
    arding
    0.36
    POSITIVE LOGITS
    惚
    0.37
     juveniles
    0.36
    뻤
    0.36
    icylic
    0.36
     occurred
    0.35
     visione
    0.34
    ouchement
    0.34
    rush
    0.34
    akana
    0.34
    lexeme
    0.34
    Activations Density 0.000%

    No Known Activations