© 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
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4939
    Prev
    Next
    INDEX
    Explanations

    llama.cpp

    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_3_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
    spapers
    2.56
    fact
    2.40
    𝚗
    2.38
    }.")
    2.36
     waxay
    2.24
     marginTop
    2.21
     "\\"
    2.17
    }})
    2.15
    }}\\
    2.15
    𝒆
    2.11
    POSITIVE LOGITS
    특별시
    2.49
    टा
    2.17
    ọc
    2.17
     preclude
    2.16
    d
    2.14
    Rigidbody
    2.14
    ième
    2.14
    能
    2.12
    dove
    2.12
    RNA
    2.09
    Activations Density 0.001%

    No Known Activations