© 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. 207781
    Prev
    Next
    INDEX
    Explanations

    pixels and numbers

    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
    ↴
    0.42
    ജി
    0.36
     totally
    0.36
     $-$
    0.36
    लियों
    0.36
     ton
    0.36
     "-"
    0.36
    ţie
    0.36
     protocols
    0.36
    صال
    0.36
    POSITIVE LOGITS
     ಸಾ
    0.43
    heaven
    0.38
     обна
    0.38
    near
    0.37
    போன்ற
    0.37
    PHOTOS
    0.36
    ineri
    0.36
    천
    0.36
     notValid
    0.35
     stolet
    0.34
    Activations Density 0.000%

    No Known Activations