© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131415
    Prev
    Next
    INDEX
    Explanations

    physical features, concepts, and events

    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_1_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
    ר
    1.59
     estradiol
    1.18
    ر
    1.16
     incandescent
    1.09
     artific
    1.09
     isomorphism
    1.06
    র
    1.01
    רות
    0.98
     Ау
    0.97
    し
    0.96
    POSITIVE LOGITS
    to
    1.26
    T
    1.25
    mr
    1.24
    mek
    1.20
    sp
    1.19
    ta
    1.18
    na
    1.18
    en
    1.17
    p
    1.16
    de
    1.13
    Activations Density 0.000%

    No Known Activations