© 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. 7216
    Prev
    Next
    INDEX
    Explanations

    strings of characters that include the letter "n" or "N", often followed by other letters or punctuation

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the letter 'n'

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

    n

    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
     disambiguazione
    -0.78
     Roskov
    -0.76
     للاسماء
    -0.75
     CiNii
    -0.75
     BoxFit
    -0.75
    GraphicsUnit
    -0.74
     Мексичка
    -0.69
    IContainer
    -0.68
    SequentialGroup
    -0.68
    ervous
    -0.68
    POSITIVE LOGITS
    n
    0.55
    ri
    0.44
    ti
    0.44
    enn
    0.43
    ill
    0.43
    timber
    0.42
    ngOnInit
    0.41
    gan
    0.40
    Lif
    0.40
    jack
    0.40
    Activations Density 1.585%

    No Known Activations