© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149858
    Prev
    Next
    INDEX
    Explanations

    say "ions"

    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
     boasted
    0.39
    ifies
    0.37
     polarised
    0.37
     glows
    0.37
     fulfils
    0.37
    ُو
    0.37
     emits
    0.36
     satisfied
    0.36
    o
    0.36
    ically
    0.35
    POSITIVE LOGITS
    IEN
    0.53
    ien
    0.51
    ierung
    0.47
    ierten
    0.46
    IAT
    0.43
    iene
    0.43
    han
    0.42
    iers
    0.42
    Arch
    0.42
    iens
    0.42
    Activations Density 0.000%

    No Known Activations