© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88629
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis

    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_60_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
     The
    0.77
     An
    0.54
    nThe
    0.48
    i
    0.44
     Ab
    0.43
    The
    0.41
     Das
    0.38
    ardust
    0.38
    l
    0.38
     Then
    0.38
    POSITIVE LOGITS
     th
    0.90
     ther
    0.63
    there
    0.63
    they
    0.59
     thei
    0.58
    their
    0.54
    these
    0.50
    थ
    0.49
    called
    0.48
    much
    0.47
    Activations Density 0.001%

    No Known Activations