© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250705
    Prev
    Next
    INDEX
    Explanations

    light sources

    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_56_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
    灯
    2.05
    燈
    2.03
     lights
    1.98
     lampu
    1.95
     lamp
    1.89
     Lights
    1.88
     lamps
    1.82
     đèn
    1.79
     Lamp
    1.75
     lighting
    1.74
    POSITIVE LOGITS
     ग्रेजुएशन
    0.39
    ティア
    0.38
     திரும
    0.37
    क्षिक
    0.36
    বায়
    0.36
     বাস
    0.35
    薏
    0.35
    বেই
    0.35
     círculo
    0.35
    ซ
    0.34
    Activations Density 0.047%

    No Known Activations