© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207192
    Prev
    Next
    INDEX
    Explanations

    declaring final variables

    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_25_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
     SALT
    0.35
    therefore
    0.34
    들과
    0.34
    uiden
    0.34
     Minds
    0.34
     salt
    0.33
     ≠
    0.33
     Aro
    0.33
     standing
    0.33
     Pul
    0.33
    POSITIVE LOGITS
     காட்சி
    0.39
     श्रेष्ठ
    0.39
    atzeko
    0.39
    샛
    0.39
    ন্যাশনাল
    0.39
    amek
    0.38
     강조
    0.38
    achelor
    0.38
    どう
    0.38
     메서
    0.38
    Activations Density 0.001%

    No Known Activations