© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14239
    Prev
    Next
    INDEX
    Explanations

    repeating or asking to hear more

    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_34_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
    Boxing
    0.39
    으
    0.38
    応援
    0.38
    কম
    0.37
    ("");
    0.37
     வி
    0.36
    मति
    0.36
    ärg
    0.36
     Boxing
    0.35
    .
    0.35
    POSITIVE LOGITS
     melakukannya
    0.46
     hacerlo
    0.41
     repeating
    0.39
     farlo
    0.38
     повторя
    0.38
    泡沫
    0.38
     Repeating
    0.37
     منها
    0.35
     repeats
    0.35
    )*
    0.35
    Activations Density 0.140%

    No Known Activations