© 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. 17737
    Prev
    Next
    INDEX
    Explanations

    by definition

    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
     द्वी
    0.39
    ime
    0.39
    olve
    0.38
     dream
    0.36
    ਈ
    0.36
    <0xD3>
    0.36
    Dream
    0.36
    english
    0.35
    тего
    0.35
    ই
    0.35
    POSITIVE LOGITS
    ඛ
    0.41
     국민
    0.38
     PUR
    0.36
     Radius
    0.35
     Gör
    0.35
     Psp
    0.35
     வடி
    0.35
    パール
    0.35
     DRS
    0.35
    図書館
    0.35
    Activations Density 0.061%

    No Known Activations