© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242693
    Prev
    Next
    INDEX
    Explanations

    sending comfort and strength

    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_40_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
    veni
    0.42
    SOLE
    0.39
    carga
    0.38
    चुरी
    0.37
    Aff
    0.37
     وصلنا
    0.37
    >?
    0.37
    }?
    0.37
     lleno
    0.36
     senso
    0.36
    POSITIVE LOGITS
     જરૂરી
    0.38
     انرژی
    0.38
     প্রয়োজনীয়
    0.38
    énergie
    0.37
     एवरी
    0.37
     SEXUAL
    0.37
     necessary
    0.36
     Necessary
    0.36
    ประจำ
    0.36
     ENERGY
    0.35
    Activations Density 0.001%

    No Known Activations