© 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. 45680
    Prev
    Next
    INDEX
    Explanations

    far beyond effort

    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
    でき
    0.44
     pumped
    0.42
     zuverläss
    0.42
     grasa
    0.42
    🙃
    0.42
     POINT
    0.42
     CORP
    0.41
    <unused693>
    0.40
     कामका
    0.39
     lubricant
    0.39
    POSITIVE LOGITS
    ghi
    0.39
    isn
    0.38
    atual
    0.38
    <0xC2>
    0.38
    is
    0.38
    zis
    0.38
    ai
    0.37
    HashMap
    0.37
     exercitation
    0.36
    miyor
    0.36
    Activations Density 0.149%

    No Known Activations