© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11306
    Prev
    Next
    INDEX
    Explanations

    building a base, preparation

    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
     ഓ
    0.48
     tét
    0.48
     አን
    0.48
     gacche
    0.48
     riêng
    0.47
     đỏ
    0.47
     InputListener
    0.46
     »,
    0.46
     {}>,
    0.46
    \%,
    0.45
    POSITIVE LOGITS
     Jenkins
    0.46
     Coaching
    0.44
     Puritan
    0.44
    getti
    0.43
    εσ
    0.43
     whilst
    0.43
     Whilst
    0.42
    iless
    0.42
    script
    0.41
    descriptors
    0.41
    Activations Density 0.026%

    No Known Activations