INDEX

Explanations

words and phrases related to scientific and technical topics, medical procedures, or specific events

oai_token-act-pair · gemini-2.0-flash

medical treatments and transactions

np_max-act · gemini-2.0-flash

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Referential

-0.70

MENAFN

-0.62

 Parthen

-0.60

 Venn

-0.60

-0.59

 Michaelis

-0.59

 raiſ

-0.57

styleType

-0.57

 Pelop

-0.57

 itſelf

-0.57

POSITIVE LOGITS

SEMICOLON

0.47

GetProperty

0.47

 recevoir

0.46

بوابة

0.46

مقد

0.45

 marquées

0.45

aluc

0.44

onta

0.44

prüche

0.43

 marqué

0.43

Activations Density 3.249%

words and phrases related to scientific and technical topics, medical procedures, or specific events

medical treatments and transactions

No Comments

No Known Activations