© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14213
    Prev
    Next
    INDEX
    Explanations

    seemingly meaningless text of mixed-origin with punctuation and single/double letter words

    oai_token-act-pair · gemini-2.0-flash

    adverbs and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    TargetException
    -0.73
    __*/
    -0.61
     CommandType
    -0.57
    uxxxx
    -0.57
    InSection
    -0.57
     AttributeSet
    -0.57
     sonno
    -0.56
     Roskov
    -0.54
     casó
    -0.53
     مشين
    -0.50
    POSITIVE LOGITS
    homonymie
    0.64
    ftance
    0.57
     >=",
    0.56
    pushFollow
    0.55
     unknownFields
    0.55
    ]();
    0.55
    MessageTagHelper
    0.54
    saraba
    0.54
    odiment
    0.54
    Vidite
    0.52
    Activations Density 1.244%

    No Known Activations