© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 4363
    Prev
    Next
    INDEX
    Explanations

    indicators of subjective feeling or evaluation, including speculation, judgement and surpise

    oai_token-act-pair · gemini-2.0-flash

    expressing opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     
    -0.53
     P
    -0.49
    ↵↵
    -0.48
     Chief
    -0.44
    </strong>
    -0.44
     '
    -0.43
     n
    -0.43
     "
    -0.41
     Ber
    -0.41
     (
    -0.41
    POSITIVE LOGITS
    AddTagHelper
    1.26
     '\\;'
    1.16
     كومونز
    1.15
    AndEndTag
    1.09
    IsContent
    1.08
     Majefty
    1.05
    MemoryWarning
    1.05
     Efq
    1.03
     uſed
    1.01
     myſelf
    1.00
    Activations Density 5.135%

    No Known Activations