© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91426
    Prev
    Next
    INDEX
    Explanations

    structured data objects

    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_11_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
    ರೆ
    0.61
    си
    0.56
    distortion
    0.54
    性は
    0.52
    راط
    0.52
    nac
    0.52
    agem
    0.51
    <0x83>
    0.51
    ен
    0.50
    acti
    0.50
    POSITIVE LOGITS
     circa
    0.66
     appointed
    0.60
    >
    0.59
     at
    0.59
    Appointment
    0.59
     europa
    0.58
    Ed
    0.56
     पर
    0.56
     RUB
    0.55
    Temple
    0.55
    Activations Density 0.000%

    No Known Activations