© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89033
    Prev
    Next
    INDEX
    Explanations

    combination with =

    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_11_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
     {
    0.69
     constat
    0.54
     refe
    0.54
     {,
    0.53
    ">)</
    0.52
     {-
    0.52
     bangunan
    0.52
     pari
    0.51
     dissoci
    0.51
     curving
    0.51
    POSITIVE LOGITS
    er
    0.82
    =
    0.64
    ي
    0.63
    elden
    0.62
     زخم
    0.62
    ر
    0.62
    搭载
    0.62
    ί
    0.61
    ние
    0.60
    eram
    0.60
    Activations Density 0.004%

    No Known Activations