© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133693
    Prev
    Next
    INDEX
    Explanations

    Apa Kabar

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     crc
    0.43
     collusion
    0.40
    aya
    0.40
    यर्स
    0.38
    ა
    0.38
    haya
    0.37
    偶尔
    0.37
    沦
    0.37
    ъл
    0.35
    ลด
    0.35
    POSITIVE LOGITS
    Kah
    0.61
    AH
    0.57
     kah
    0.57
    kah
    0.56
    ah
    0.55
     ah
    0.54
     AH
    0.53
     Kah
    0.52
     Ah
    0.46
    اه
    0.46
    Activations Density 0.007%

    No Known Activations