© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58769
    Prev
    Next
    INDEX
    Explanations

    tamp, Temp, Property Taxes, Taman Negara

    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_2_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
    1.70
     the
    1.09
    ς
    1.06
    ی
    0.98
     behest
    0.96
    ,
    0.93
    the
    0.92
    ments
    0.91
    이니까
    0.88
    𝘀
    0.88
    POSITIVE LOGITS
    на
    1.26
    ר
    1.19
    р
    1.13
    ل
    1.11
    .
    1.10
    (
    1.05
    يل
    1.05
    м
    1.04
     .
    1.03
     (
    1.02
    Activations Density 0.004%

    No Known Activations