© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37244
    Prev
    Next
    INDEX
    Explanations

    Swiss Federal Statistical Office

    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_3_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
    {
    0.88
    1
    0.74
    0
    0.70
    +
    0.65
    );
    0.64
    _{
    0.64
    <0x80>
    0.59
    3
    0.59
    【
    0.59
    {$
    0.57
    POSITIVE LOGITS
    ল
    0.88
    л
    0.82
    ल
    0.80
    ید
    0.68
    ل
    0.68
    ью
    0.68
    ChooseCharacter
    0.64
    اقة
    0.64
     BusABC
    0.61
     aceea
    0.61
    Activations Density 0.001%

    No Known Activations