© 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. 1978
    Prev
    Next
    INDEX
    Explanations

    words starting with "semi-"

    oai_token-act-pair · gemini-2.0-flash

    terms related to semi-conductors

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

    sem

    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
     an
    -0.48
     détaillés
    -0.48
     le
    -0.42
    —
    -0.41
     sebaik
    -0.40
    mejor
    -0.40
    sikal
    -0.39
     a
    -0.39
    Varint
    -0.38
    ::~
    -0.38
    POSITIVE LOGITS
     disambiguazione
    1.12
    RenderAtEndOf
    1.05
    hyrchwyd
    0.99
     myſelf
    0.88
    Демографія
    0.84
    tangentMode
    0.81
     bezeichneter
    0.81
     Efq
    0.81
     Majefty
    0.79
     doubtnut
    0.78
    Activations Density 0.643%

    No Known Activations