© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4543
    Prev
    Next
    INDEX
    Explanations

    various code snippets in different programming languages

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natur
    -0.49
    Bibliografia
    -0.40
    حياته
    -0.40
    entend
    -0.40
    ின்
    -0.40
     lebih
    -0.40
     صوتيه
    -0.40
     وف
    -0.39
    databinding
    -0.39
    PLEMENT
    -0.39
    POSITIVE LOGITS
    ftagPool
    0.66
    RenderAtEndOf
    0.60
     Majefty
    0.58
     Umm
    0.58
     doubtnut
    0.56
    تقاوى
    0.56
    AndEndTag
    0.53
    ishable
    0.53
    المناصب
    0.53
    }{*}{}
    0.52
    Activations Density 4.980%

    No Known Activations