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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14664
    Prev
    Next
    INDEX
    Explanations

    parts of a music review

    oai_token-act-pair · gemini-2.0-flash

    music and song lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ValueStyle
    -0.62
     Normdatei
    -0.47
     vicenda
    -0.47
     getRule
    -0.47
    PullParser
    -0.46
    NullCheck
    -0.46
     Guides
    -0.46
     episodio
    -0.45
     Episodes
    -0.43
     episodes
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.68
     useRef
    0.64
    äischen
    0.59
     مشين
    0.59
    gnition
    0.55
    FECT
    0.55
    oustic
    0.55
     acoustic
    0.54
     Савезне
    0.54
    ersdorf
    0.53
    Activations Density 0.896%

    No Known Activations