© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46070
    Prev
    Next
    INDEX
    Explanations

    things while also

    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_13_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
    étaient
    0.25
    eta
    0.25
    ce
    0.24
    m
    0.24
    hostname
    0.23
    bae
    0.23
    sa
    0.23
    etable
    0.23
    ewo
    0.23
    rept
    0.23
    POSITIVE LOGITS
    рта
    0.24
     accession
    0.23
     UT
    0.23
     veritable
    0.22
     tinkering
    0.22
    তীত
    0.22
     FAU
    0.22
    к
    0.22
     dismantle
    0.21
     Alessandra
    0.21
    Activations Density 0.011%

    No Known Activations