© 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. 14171
    Prev
    Next
    INDEX
    Explanations

    proper names and locations

    oai_token-act-pair · gemini-2.0-flash

    names of authors or publications

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

    Scientific papers

    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
    AddTagHelper
    -0.81
     InputDecoration
    -0.64
     viewDidLoad
    -0.61
    });
    -0.53
     useParams
    -0.50
     noqa
    -0.49
     PyTuple
    -0.47
    Lähteet
    -0.46
     crutches
    -0.46
    }));
    -0.46
    POSITIVE LOGITS
     aveug
    0.62
    scher
    0.60
     виправивши
    0.60
    oredCriteria
    0.58
    Datuak
    0.55
     VIDEOTAPE
    0.54
    räck
    0.54
    存于互联网档案馆
    0.54
     sauvage
    0.53
     coû
    0.53
    Activations Density 0.205%

    No Known Activations