© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 214761
    Prev
    Next
    INDEX
    Explanations

    four pairs

    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_16_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
     поверхность
    0.56
    ه
    0.56
    a
    0.55
    ⛧
    0.55
    бурге
    0.54
    া
    0.54
     inappropri
    0.52
    𝓵
    0.52
    aita
    0.51
     грошы
    0.51
    POSITIVE LOGITS
    编码
    0.52
     coded
    0.48
     target
    0.46
     coding
    0.46
     PPE
    0.46
     structure
    0.45
     representation
    0.42
     forms
    0.42
     species
    0.41
    coding
    0.41
    Activations Density 0.000%

    No Known Activations