INDEX

Explanations

words related to scientific publications and journals

oai_token-act-pair · gemini-2.0-flash

Virology journals

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gre

-0.63

 material

-0.52

Ắ

-0.50

cuadro

-0.50

Jîn

-0.50

 impar

-0.49

MathML

-0.49

 univers

-0.49

 final

-0.48

 nature

-0.48

POSITIVE LOGITS

ConstraintMaker

0.98

 vettoriale

0.85

 onOptions

0.83

twimg

0.80

AxisAlignment

0.79

 ouvriers

0.79

 يتيمه

0.78

 kasarigan

0.78

WebVitals

0.77

bootstrapcdn

0.75

Activations Density 0.985%

words related to scientific publications and journals

Virology journals

No Comments

No Known Activations