© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3144
    Prev
    Next
    INDEX
    Explanations

    generations and financial inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ⌇
    1.17
    푎
    1.13
     !}
    1.12
    ⎙
    1.11
     Elke
    1.11
     prerequisite
    1.09
    ⃞
    1.09
    DebugType
    1.08
    ateau
    1.08
    }=-\
    1.08
    POSITIVE LOGITS
    en
    1.18
     soal
    1.10
    ሲ
    1.08
    된
    1.04
    debate
    1.01
    hetic
    1.01
    ن
    0.99
    문제
    0.99
    rece
    0.96
    dor
    0.96
    Activations Density 0.043%

    No Known Activations