© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206591
    Prev
    Next
    INDEX
    Explanations

    all come together

    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_46_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
     promot
    0.39
    断
    0.39
     جانب
    0.37
    귀
    0.37
     осозна
    0.36
    斷
    0.36
     depiction
    0.35
    DAR
    0.35
     귀
    0.35
    áctica
    0.35
    POSITIVE LOGITS
     партне
    0.48
     Pairing
    0.42
     pairing
    0.41
    োসিয়ে
    0.40
    pele
    0.39
    andt
    0.39
     shouting
    0.38
     amazing
    0.38
     merav
    0.38
    uerdo
    0.38
    Activations Density 0.001%

    No Known Activations