© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13430
    Prev
    Next
    INDEX
    Explanations

    writing to file (

    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_13_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
    frü
    0.73
    ero
    0.65
    move
    0.59
    çı
    0.59
    eno
    0.58
    lift
    0.58
    å
    0.57
    olo
    0.57
    playing
    0.57
    ě
    0.57
    POSITIVE LOGITS
     работ
    0.60
     обяза
    0.58
     bimod
    0.57
    𝜆
    0.57
     chairperson
    0.55
     menging
    0.54
    맟
    0.54
     phosphoryl
    0.54
     requisitos
    0.54
     multiplica
    0.54
    Activations Density 0.036%

    No Known Activations