© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4422
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to a broad set of various situations and topics.

    oai_token-act-pair · gemini-2.0-flash

    words with unique or archaic spellings

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

    Discussions about subjects

    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
    haped
    -0.49
    #+#
    -0.46
     nakalista
    -0.42
    justed
    -0.41
    verständlich
    -0.41
    nickname
    -0.41
     chicos
    -0.40
     mej
    -0.40
    cerpts
    -0.40
     Besøkt
    -0.39
    POSITIVE LOGITS
    Jereo
    0.91
     houſe
    0.79
     Jefus
    0.75
     Houſe
    0.72
    ChromeDriver
    0.70
     Conſ
    0.69
     ſche
    0.68
     виправивши
    0.66
     reticulum
    0.65
     uſed
    0.65
    Activations Density 11.126%

    No Known Activations