© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82281
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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_53_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
     dine
    0.53
     sine
    0.49
    嘍
    0.44
    мина
    0.43
    otine
    0.42
    飲食
    0.41
     sina
    0.41
    alarını
    0.40
     Dine
    0.40
     своих
    0.39
    POSITIVE LOGITS
    Pon
    0.40
     cé
    0.36
    Sim
    0.35
    Pare
    0.35
    㥆
    0.35
     вза
    0.35
     sợ
    0.35
    ṣ
    0.35
    cens
    0.34
    Oreal
    0.34
    Activations Density 0.001%

    No Known Activations