© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15296
    Prev
    Next
    INDEX
    Explanations

    phrases "of choice" or "of [modality]"

    oai_token-act-pair · gemini-2.0-flash

    unexpected tokens or terms

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

    choices and options

    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
     of
    -2.41
     của
    -1.32
    ของ
    -1.27
    of
    -1.09
     ofthe
    -1.06
    ofthe
    -0.96
    Of
    -0.90
     Of
    -0.88
    OfThe
    -0.88
     ของ
    -0.86
    POSITIVE LOGITS
    évaluateur
    0.52
     Meksiku
    0.48
    ++)
    0.47
    )");
    0.45
    TagHelper
    0.44
    ⓧ
    0.43
    }",
    0.42
     Krakowie
    0.42
    fieldId
    0.41
    chimp
    0.41
    Activations Density 1.359%

    No Known Activations