© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150256
    Prev
    Next
    INDEX
    Explanations

    ink application or ribbon

    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_23_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
     resigned
    0.41
     novembro
    0.41
    ignation
    0.41
     реализу
    0.40
     besieged
    0.40
     ===
    0.39
    ringen
    0.38
     defra
    0.38
     कनेक्टिव
    0.38
     नवंबर
    0.38
    POSITIVE LOGITS
    AIS
    0.41
    ༦
    0.40
    PLIC
    0.39
    PAT
    0.39
    plic
    0.38
    Liter
    0.37
    ולם
    0.36
    ÕES
    0.36
    Toy
    0.35
    incar
    0.35
    Activations Density 0.000%

    No Known Activations