© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208936
    Prev
    Next
    INDEX
    Explanations

    trip plans

    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_10_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
    Okno
    0.56
    Strafpunkte
    0.52
     الجرس
    0.52
    Detailed
    0.52
     أول
    0.50
    }$;
    0.50
    㫙
    0.50
    }$.
    0.48
    Sock
    0.47
    Cosine
    0.47
    POSITIVE LOGITS
    u
    0.56
    ї
    0.46
    ig
    0.44
     FAO
    0.44
    if
    0.43
    pada
    0.43
     communes
    0.43
     akik
    0.42
    パー
    0.42
     FAB
    0.42
    Activations Density 0.000%

    No Known Activations