© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11825
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to business, law, time and geography

    oai_token-act-pair · gemini-2.0-flash

    technical terms and identifiers

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

    Formal documents

    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
     .
    -0.53
    遇
    -0.47
     مُعرِّف
    -0.46
    _
    -0.46
     Ganz
    -0.45
    -
    -0.45
     Rady
    -0.44
    /.
    -0.44
    ?.
    -0.44
     Bright
    -0.44
    POSITIVE LOGITS
    featureID
    0.81
     AttributeSet
    0.80
     мәкал
    0.74
    LLocation
    0.70
    Referencie
    0.67
    contentLoaded
    0.66
    abestanden
    0.66
    +#+
    0.66
    $")
    0.65
    ]";
    0.65
    Activations Density 2.051%

    No Known Activations