© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8631
    Prev
    Next
    INDEX
    Explanations

    the beginning of the name "Ste..." or "Sti..."

    oai_token-act-pair · gemini-2.0-flash

    variations of the prefix 'Ste'

    np_token-act-pair-logits · gpt-4o-mini

    Ste

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     समीक्षक
    -0.59
    Step
    -0.49
     Step
    -0.45
     step
    -0.45
    step
    -0.42
    Solution
    -0.41
    sizeCache
    -0.40
    igrette
    -0.38
    dri
    -0.38
    ley
    -0.36
    POSITIVE LOGITS
    Geplaatst
    0.75
    Obrázky
    0.66
     سكانية
    0.63
    NameInMap
    0.63
    Erreferentziak
    0.61
    imbawa
    0.61
    newtheorem
    0.61
    bosky
    0.60
    fjspx
    0.60
    //
    0.60
    Activations Density 0.267%

    No Known Activations