© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215995
    Prev
    Next
    INDEX
    Explanations

    front

    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_47_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
     hinter
    0.54
     achter
    0.53
    バック
    0.50
     背
    0.50
    背
    0.49
     ব্যাক
    0.48
     Back
    0.47
     پشت
    0.47
     백
    0.45
     बैक
    0.44
    POSITIVE LOGITS
    前
    1.91
     front
    1.89
     앞
    1.89
    的前
    1.86
    앞
    1.84
     delante
    1.82
     前
    1.77
     devant
    1.77
     davanti
    1.77
     ahead
    1.72
    Activations Density 0.001%

    No Known Activations