© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196455
    Prev
    Next
    INDEX
    Explanations

    locations of places

    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_15_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
    public
    0.52
    Delta
    0.51
    name
    0.51
    Ho
    0.51
    1
    0.50
    come
    0.49
    jo
    0.49
    fin
    0.48
    +'
    0.48
    Pass
    0.48
    POSITIVE LOGITS
     көрс
    0.55
     limón
    0.55
    يكا
    0.53
    যজ্ঞ
    0.53
    チョコレート
    0.53
     $>
    0.50
     സിനിമ
    0.50
    BUGFS
    0.50
     ricost
    0.50
     Bhosle
    0.50
    Activations Density 0.000%

    No Known Activations