© 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. 205259
    Prev
    Next
    INDEX
    Explanations

    assume assumptions

    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
    Works
    0.49
     works
    0.44
     Works
    0.43
     potest
    0.40
     ?-
    0.39
    ష్య
    0.38
    ?—
    0.38
    Facet
    0.38
    燵
    0.37
    works
    0.37
    POSITIVE LOGITS
     assume
    0.50
     assumed
    0.49
     don
    0.48
     assumes
    0.46
    assume
    0.45
     ..
    0.41
     Don
    0.40
     assumptions
    0.40
    Assume
    0.40
     assum
    0.40
    Activations Density 0.006%

    No Known Activations