© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140429
    Prev
    Next
    INDEX
    Explanations

    ebay item link

    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_12_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
    ين
    0.13
    ,
    0.12
     adjudicated
    0.12
    నాలను
    0.11
    ادي
    0.11
    ق
    0.11
    譲
    0.11
     expediency
    0.11
    െങ്കിലും
    0.11
    ﻗ
    0.11
    POSITIVE LOGITS
     शकतात
    0.13
    »
    0.13
    Cedar
    0.13
     t
    0.13
    Okay
    0.13
    Finger
    0.13
    «
    0.13
    Occ
    0.12
    Highway
    0.12
    Hight
    0.12
    Activations Density 0.001%

    No Known Activations