© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45566
    Prev
    Next
    INDEX
    Explanations

    repeat other steps

    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_22_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
     Subst
    0.45
    갛
    0.44
     Existing
    0.44
    ประจำ
    0.40
     besta
    0.40
    炎症
    0.40
    স্তর
    0.39
    хема
    0.39
    स्तर
    0.39
     Consistent
    0.38
    POSITIVE LOGITS
     }}\
    0.39
    ils
    0.38
    luk
    0.38
    ᠲ
    0.38
    掘
    0.37
    icolored
    0.37
     மற்றொரு
    0.37
     nugget
    0.37
     nug
    0.36
    adihi
    0.36
    Activations Density 0.004%

    No Known Activations