© 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. 3934
    Prev
    Next
    INDEX
    Explanations

    character sequences with the letter A and some other letters directly after it

    oai_token-act-pair · gemini-2.0-flash

    foreign language tokens or characters

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

    URLs and code

    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
    '];?>
    -0.56
    '],'
    -0.55
    ++]=
    -0.54
    "]}
    -0.54
    IVEREF
    -0.54
    ']);
    -0.53
    ']);
    -0.53
    jare
    -0.52
    "?>
    -0.52
     VIDE
    -0.51
    POSITIVE LOGITS
    venido
    0.59
     imidlertid
    0.59
     câte
    0.58
     dårlig
    0.57
     mourut
    0.57
     moeite
    0.57
     lær
    0.57
     oscuros
    0.57
     fût
    0.56
    zelfde
    0.55
    Activations Density 0.691%

    No Known Activations