© 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. 7832
    Prev
    Next
    INDEX
    Explanations

    common short words like "at", "in", "to", "for", "from", "with", "that", "as", "be", and "on"

    oai_token-act-pair · gemini-2.0-flash

    determiners and pronouns

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

    at

    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
     useContext
    -0.71
    ExtendWith
    -0.66
    esModule
    -0.66
    SequentialGroup
    -0.65
    /**
    -0.64
    NOPQRST
    -0.63
    copg
    -0.62
    setof
    -0.60
    imageshack
    -0.60
     venons
    -0.60
    POSITIVE LOGITS
     the
    0.89
     this
    0.64
     their
    0.62
     its
    0.61
     a
    0.60
     these
    0.59
     that
    0.57
     your
    0.56
     some
    0.54
     our
    0.54
    Activations Density 16.880%

    No Known Activations