© 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. 145815
    Prev
    Next
    INDEX
    Explanations

    ir / root

    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
     Eri
    0.44
    Erin
    0.43
     эр
    0.40
     Эр
    0.40
     Erin
    0.37
    थुरा
    0.37
    omé
    0.37
    擦
    0.37
     ERK
    0.36
    aré
    0.36
    POSITIVE LOGITS
    ir
    1.75
     ir
    1.66
     Ir
    1.53
    Ir
    1.45
     irr
    1.43
     IR
    1.33
     Irving
    1.29
    IR
    1.20
     Irwin
    1.16
    Irr
    1.16
    Activations Density 0.002%

    No Known Activations