© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151406
    Prev
    Next
    INDEX
    Explanations

    SOLID principles and IBM

    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_18_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
     jealousy
    0.15
     ladder
    0.13
    ys
    0.13
    yl
    0.12
     liquor
    0.12
    h
    0.12
    jesi
    0.12
     ladders
    0.12
    autos
    0.12
     collaborating
    0.12
    POSITIVE LOGITS
    ⇉
    0.14
    Incre
    0.14
     됩니다
    0.13
     खेलकर
    0.13
    월
    0.12
    имость
    0.12
    ✹
    0.12
    Shuffle
    0.12
    런치
    0.12
     înviat
    0.12
    Activations Density 0.001%

    No Known Activations