© 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. 13310
    Prev
    Next
    INDEX
    Explanations

    studio and workshop spaces

    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
     বিবাহ
    0.47
     besonder
    0.46
    espresso
    0.45
    ]
    0.44
     пользователей
    0.43
    ದ್ಧ
    0.42
     utenti
    0.42
     ഒന്നും
    0.42
     umani
    0.40
     ultrast
    0.40
    POSITIVE LOGITS
    aría
    0.46
    ņu
    0.45
    포
    0.44
    obic
    0.44
    بوون
    0.43
    ويب
    0.43
     cariño
    0.43
     EIR
    0.42
    ান্
    0.42
    ło
    0.41
    Activations Density 0.010%

    No Known Activations