© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6932
    Prev
    Next
    INDEX
    Explanations

    references to mental health issues

    oai_token-act-pair · gemini-2.0-flash

    Dealing with problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    pidou
    -0.59
    YECTO
    -0.54
    ESSOR
    -0.52
     Budaya
    -0.52
    otheek
    -0.51
     Mühle
    -0.49
    mbolo
    -0.49
     Philosop
    -0.49
     BrowserModule
    -0.49
     PAINTING
    -0.49
    POSITIVE LOGITS
    ]")]
    0.80
     Signalez
    0.68
    httphttps
    0.66
    UserScript
    0.63
     متعلقه
    0.62
    ConstraintMaker
    0.61
    发表于
    0.58
     snippetHide
    0.57
    KommentareTeilen
    0.56
    LookAnd
    0.55
    Activations Density 22.878%

    No Known Activations