© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121906
    Prev
    Next
    INDEX
    Explanations

    Steve followed by surname

    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_3_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
    am
    0.64
    {
    0.63
    };
    0.61
    ad
    0.60
    ay
    0.59
    atrical
    0.56
    imab
    0.55
    O
    0.55
    ar
    0.54
    ot
    0.54
    POSITIVE LOGITS
    gador
    0.58
     polypeptide
    0.57
     Toán
    0.56
     লো
    0.55
    и
    0.55
    യാണ്
    0.55
    ﻚ
    0.53
    ką
    0.53
     желание
    0.52
    一种
    0.52
    Activations Density 0.000%

    No Known Activations