© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88479
    Prev
    Next
    INDEX
    Explanations

    affirmation or agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    ക്ര
    0.28
     DBE
    0.28
     meses
    0.26
     firms
    0.25
    ‑
    0.25
     also
    0.25
     фирмы
    0.25
     Benn
    0.25
     relaciones
    0.25
    벤
    0.25
    POSITIVE LOGITS
     அமிலம்
    0.30
    టు
    0.27
    abv
    0.27
    Joy
    0.26
    喲
    0.26
    hatiti
    0.25
     Mali
    0.25
    Cutting
    0.25
     joy
    0.25
    Sunday
    0.25
    Activations Density 0.005%

    No Known Activations