© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11847
    Prev
    Next
    INDEX
    Explanations

    words starting with "Sh" plus other random words throughout several different documents; this neuron doesn't seem to have a single focus.

    oai_token-act-pair · gemini-2.0-flash

    sh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     sh
    -1.31
     Sh
    -1.28
    Sh
    -1.23
    sh
    -1.20
     SH
    -1.02
    SH
    -0.98
     shi
    -0.89
    Sha
    -0.73
    Shi
    -0.72
     Sha
    -0.71
    POSITIVE LOGITS
     HMI
    0.73
     HCM
    0.69
    HtmlAttribute
    0.63
     Hopf
    0.63
    CHM
    0.61
     subgoal
    0.59
    HCI
    0.58
     HJ
    0.57
     Hera
    0.57
     subgoals
    0.57
    Activations Density 4.955%

    No Known Activations