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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12790
    Prev
    Next
    INDEX
    Explanations

    a variety of very specific terms that nonetheless fall into a limited number of semantic categories

    oai_token-act-pair · 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
    providedIn
    -0.58
    )':
    -0.53
    úcia
    -0.51
    uxxxx
    -0.51
    ://"
    -0.50
    ïe
    -0.49
    dolu
    -0.46
    дента
    -0.46
    bian
    -0.46
    --;
    -0.45
    POSITIVE LOGITS
     Chriftian
    0.60
    __*/
    0.59
     greateſt
    0.59
     Jefus
    0.58
     Chrift
    0.57
    ſelf
    0.57
    jsonwebtoken
    0.56
    ſelves
    0.55
     Monfieur
    0.55
    TestingModule
    0.54
    Activations Density 1.030%

    No Known Activations