INDEX

Explanations

strings of text that are part of figure captions or descriptions in scientific writing

oai_token-act-pair · gemini-2.0-flash

group

np_max-act · gemini-2.0-flash

New Auto-Interp

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

<bos>

-0.89

 MainAxisSize

-0.70

AutoresizingMask

-0.57

 كومونز

-0.50

 umano

-0.49

Intr

-0.49

SequentialGroup

-0.49

‍♂️

-0.49

 choisissez

-0.49

 dénon

-0.48

POSITIVE LOGITS

Scénario

0.68

Espèce

0.67

igshid

0.64

 protoimpl

0.61

TagMode

0.60

govina

0.59

 <<<<<<<<<<<<<<

0.56

 contextLoads

0.55

GeoNames

0.54

 calendriers

0.54

Activations Density 3.256%

strings of text that are part of figure captions or descriptions in scientific writing

group

No Comments

No Known Activations