© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130139
    Prev
    Next
    INDEX
    Explanations

    anhedonia / unmarshal

    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
    다
    1.20
    j
    1.09
    но
    1.09
    на
    1.08
    ри
    1.05
    в
    1.02
    리
    1.02
    ड
    1.00
     subdued
    0.99
    ד
    0.99
    POSITIVE LOGITS
     and
    1.31
     or
    1.19
    ando
    1.02
    with
    1.02
    and
    1.00
    써
    0.99
    ة
    0.98
    ja
    0.97
    onom
    0.94
    iers
    0.91
    Activations Density 0.000%

    No Known Activations