© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15925
    Prev
    Next
    INDEX
    Explanations

    questions, problems, or suggestions

    oai_token-act-pair · gemini-2.0-flash

    problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    AndEndTag
    -0.72
     houſe
    -0.71
     Efq
    -0.69
     Roskov
    -0.68
     myſelf
    -0.68
    ähteet
    -0.67
     gynhyrchwyd
    -0.66
     Monfieur
    -0.65
     ftate
    -0.65
     yoox
    -0.65
    POSITIVE LOGITS
     only
    0.43
     INTERESAR
    0.41
    JsonIgnore
    0.39
    ap
    0.39
    Jegyzetek
    0.39
    only
    0.38
     catch
    0.38
     nó
    0.37
     Vikipedi
    0.37
     I
    0.37
    Activations Density 2.726%

    No Known Activations