© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150380
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     راجس
    0.51
     structuring
    0.45
     pab
    0.45
    ورسٹی
    0.45
    ikiem
    0.44
    㖣
    0.44
     ruangan
    0.43
    ctuations
    0.43
     கொண்டிருந்த
    0.43
    간
    0.43
    POSITIVE LOGITS
    á
    0.72
    s
    0.61
    z
    0.58
    j
    0.53
    Ἄ
    0.53
    h
    0.52
    c
    0.52
    BC
    0.50
    er
    0.50
    ي
    0.49
    Activations Density 0.000%

    No Known Activations