© 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. 9458
    Prev
    Next
    INDEX
    Explanations

    words related to gifts and holidays, especially associated with pink and/or wrapping

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'conf'

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

    candy and parties

    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
    apunov
    -0.64
     codec
    -0.61
     protoimpl
    -0.59
    beke
    -0.57
     BoxFit
    -0.57
     pamamagitan
    -0.54
     surla
    -0.52
     Fleetwood
    -0.52
     MenuView
    -0.52
     kaban
    -0.52
    POSITIVE LOGITS
    conf
    0.65
    Personendaten
    0.65
     שוליים
    0.65
     conf
    0.63
     helium
    0.59
     Conf
    0.56
    djangoproject
    0.56
    Party
    0.54
    party
    0.54
    Conf
    0.53
    Activations Density 1.082%

    No Known Activations