© 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. 205500
    Prev
    Next
    INDEX
    Explanations

    logical operators

    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
    ###
    0.53
    ##
    0.45
    .#
    0.43
     (#
    0.42
     Includes
    0.41
    #
    0.41
     Works
    0.41
    (${
    0.40
    ####
    0.39
     (${
    0.39
    POSITIVE LOGITS
     ==
    0.63
     !=
    0.56
     isn
    0.52
     isnt
    0.51
     /=
    0.51
     wasnt
    0.47
     legyen
    0.45
    يكون
    0.45
     :=
    0.44
     নয়
    0.44
    Activations Density 0.004%

    No Known Activations