© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140981
    Prev
    Next
    INDEX
    Explanations

    eggs, dozen, refrigerator

    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_12_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
    ]
    0.52
     Dét
    0.48
    okon
    0.46
     decon
    0.45
     середи
    0.44
    }
    0.44
    igeon
    0.43
    egaard
    0.43
     {
    0.43
    offs
    0.42
    POSITIVE LOGITS
    ר
    0.58
     Fleurs
    0.56
    र
    0.55
    वक
    0.52
    dır
    0.52
    ധിക
    0.51
    w
    0.51
    ग
    0.51
    щ
    0.51
    ｋ
    0.51
    Activations Density 0.001%

    No Known Activations