© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81933
    Prev
    Next
    INDEX
    Explanations

    come

    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_53_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
    ]")
    0.39
    bringen
    0.38
     zuverläss
    0.38
    japan
    0.38
    뻗
    0.37
    <0xCD>
    0.36
    inu
    0.36
    thenReturn
    0.35
    মেঘ
    0.35
    ឌ
    0.35
    POSITIVE LOGITS
     Taylor
    0.37
    Void
    0.37
    St
    0.37
    ሳይ
    0.36
     Sam
    0.36
     Void
    0.36
     Little
    0.35
    aye
    0.35
     سام
    0.35
     St
    0.35
    Activations Density 0.003%

    No Known Activations