© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179162
    Prev
    Next
    INDEX
    Explanations

    results followed by findings

    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_29_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
    קור
    0.44
    ⚛
    0.43
     정확
    0.39
     Kxb
    0.39
     തൊ
    0.39
     పరీక్ష
    0.38
     වඩා
    0.38
     впли
    0.38
     करीबी
    0.36
     러
    0.36
    POSITIVE LOGITS
    mias
    0.47
    ococ
    0.41
     marinas
    0.40
    みの
    0.39
    hältnis
    0.39
     merchandising
    0.38
    endes
    0.38
     Verhältnis
    0.37
    citep
    0.36
    ouble
    0.36
    Activations Density 0.000%

    No Known Activations