© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82317
    Prev
    Next
    INDEX
    Explanations

    f

    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_53_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
     objectForKey
    0.40
     duis
    0.39
    ʑ
    0.38
    टका
    0.37
    NB
    0.35
    羸
    0.35
    Lap
    0.35
    慨
    0.35
     크
    0.34
    خری
    0.34
    POSITIVE LOGITS
     f
    1.37
     ف
    1.25
     ফ
    1.19
     फ
    1.07
    f
    1.06
    ฟ
    1.01
     ф
    0.99
    <0x86>
    0.92
     فَ
    0.89
     फ़
    0.88
    Activations Density 0.004%

    No Known Activations