© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5742
    Prev
    Next
    INDEX
    Explanations

    know, knew, new

    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_39_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
     insure
    0.40
    }):
    0.37
     डालें
    0.36
    :'',
    0.36
    τητα
    0.36
    えられる
    0.36
     করিয়াছেন
    0.35
    }[(
    0.35
    शनल
    0.35
     insures
    0.34
    POSITIVE LOGITS
    agic
    0.44
     فرو
    0.39
    ধে
    0.38
    stairs
    0.38
    utors
    0.38
    utor
    0.37
     Hsu
    0.37
    guardian
    0.36
     തൊ
    0.36
     Hands
    0.36
    Activations Density 0.049%

    No Known Activations