INDEX

Explanations

text from an internet chat in French.

oai_token-act-pair · gemini-2.0-flash

Mais

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

 EconPapers

-0.62

 pleaſure

-0.60

the

-0.59

 raiſ

-0.58

IsContent

-0.57

 Monfieur

-0.56

utives

-0.56

terness

-0.55

 unknownFields

-0.55

 ExecuteAsync

-0.53

POSITIVE LOGITS

帖最后由

0.70

 estekak

0.57

formik

0.52

 internetowa

0.50

 onFailure

0.50

addCriterion

0.50

WebMethod

0.49

romyal

0.49

 piaci

0.49

Activations Density 1.073%

text from an internet chat in French.

Mais

No Comments

No Known Activations