© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148353
    Prev
    Next
    INDEX
    Explanations

    transf

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    u
    0.56
     SME
    0.39
    MORE
    0.39
     detriment
    0.38
     felt
    0.37
     superhero
    0.36
    Marian
    0.36
     slab
    0.35
    <sub>
    0.35
    uve
    0.35
    POSITIVE LOGITS
    d
    0.45
    lı
    0.45
    lardan
    0.45
    larım
    0.44
    lera
    0.44
    ell
    0.44
    рот
    0.43
    <0xBA>
    0.43
    l
    0.43
    ligen
    0.43
    Activations Density 0.000%

    No Known Activations