© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194983
    Prev
    Next
    INDEX
    Explanations

    amperage rating

    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_4_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
    ни
    1.20
    на
    1.13
    ام
    1.07
    tas
    0.96
    <0x0D>
    0.93
    ко
    0.91
    يل
    0.86
    ni
    0.84
    ంది
    0.83
    ne
    0.81
    POSITIVE LOGITS
    ও
    1.13
    CA
    1.07
    ای
    1.05
    ES
    1.05
    פ
    1.04
    it
    1.01
    PE
    1.01
    P
    1.00
    Please
    0.96
    PP
    0.96
    Activations Density 0.001%

    No Known Activations