© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208669
    Prev
    Next
    INDEX
    Explanations

    fl

    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_56_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
     b
    2.16
     б
    1.52
     ب
    1.44
     ब
    1.40
     ব
    1.39
    b
    1.26
    <0x99>
    1.23
    บ
    1.20
     ב
    1.05
    б
    0.96
    POSITIVE LOGITS
     fl
    1.64
    fl
    0.73
     Fl
    0.53
     t
    0.46
     flyers
    0.46
    Fl
    0.41
     flie
    0.40
     Tets
    0.39
     flute
    0.39
     Flan
    0.38
    Activations Density 0.002%

    No Known Activations