© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195580
    Prev
    Next
    INDEX
    Explanations

    technical and scientific

    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_50_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
    sid
    0.50
    <0x8A>
    0.50
    yd
    0.47
    idt
    0.47
    idi
    0.46
    idos
    0.45
    Sid
    0.44
     IT
    0.44
    ider
    0.44
    idum
    0.44
    POSITIVE LOGITS
    atz
    0.44
    рим
    0.40
    achts
    0.39
    ಾಂ
    0.38
    apine
    0.37
    atin
    0.37
    atience
    0.37
    쟁
    0.36
     методом
    0.36
     katta
    0.36
    Activations Density 0.007%

    No Known Activations