© 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. 9332
    Prev
    Next
    INDEX
    Explanations

    terms related to the validity of an idea or assertion

    oai_token-act-pair · gemini-2.0-flash

    clauses introducing explanations or claims

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

    claims/hypotheses

    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
    IonicModule
    -0.69
     appelez
    -0.59
    izoen
    -0.53
     deje
    -0.52
    asticity
    -0.51
    Vidite
    -0.50
     Comprometido
    -0.50
     Anſ
    -0.50
    ölcs
    -0.49
    Jonah
    -0.48
    POSITIVE LOGITS
     that
    0.86
     selon
    0.77
     πως
    0.70
     ότι
    0.68
     dass
    0.65
    })));
    0.63
     secondo
    0.61
     että
    0.60
     что
    0.60
     according
    0.59
    Activations Density 2.821%

    No Known Activations