© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62516
    Prev
    Next
    INDEX
    Explanations

    whose

    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_59_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
     Existence
    0.45
     exists
    0.44
     Role
    0.42
     Who
    0.41
     ROLE
    0.41
     who
    0.40
    presence
    0.39
    ’
    0.39
     présence
    0.38
    dimensionality
    0.38
    POSITIVE LOGITS
     job
    0.50
    Job
    0.45
    job
    0.39
    JOB
    0.38
    Most
    0.38
     inescapable
    0.37
    Alleg
    0.37
     alleged
    0.36
     permanent
    0.36
    Tim
    0.36
    Activations Density 0.002%

    No Known Activations