© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45859
    Prev
    Next
    INDEX
    Explanations

    SO₄²⁻, Cl⁻, H₂O, NO₃⁻

    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_10_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
    s
    0.92
    }
    0.84
    to
    0.82
    t
    0.77
    n
    0.73
    บ
    0.73
    k
    0.71
    าน
    0.67
    r
    0.67
    ل
    0.66
    POSITIVE LOGITS
     calend
    0.57
     calendars
    0.56
    arbeiten
    0.54
    jectory
    0.54
    ohl
    0.52
    endering
    0.52
    cutter
    0.52
    τη
    0.51
    arbeit
    0.51
    azoned
    0.51
    Activations Density 0.001%

    No Known Activations