© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 91912
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions or descriptions

    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_11_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
    フランス
    0.60
     niveaux
    0.55
     ethnicities
    0.55
    의
    0.55
     avec
    0.52
    スメ
    0.52
    kých
    0.52
    法国
    0.51
     exécut
    0.51
    Д
    0.51
    POSITIVE LOGITS
    illa
    0.60
    lica
    0.57
    illä
    0.56
    }:=
    0.54
    }
    0.54
    ida
    0.53
    }');
    0.53
    ean
    0.52
     তাড়াতাড়ি
    0.52
    ela
    0.52
    Activations Density 0.047%

    No Known Activations