INDEX

Explanations

words relating to future possibility

oai_token-act-pair · gemini-2.0-flash

possibility and uncertainty

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

########.

-0.75

<?

-0.71

 noqa

-0.67

oa̍t

-0.59

 لينك

-0.58

RenderAtEndOf

-0.54

 PyLong

-0.53

+#+

-0.52

ToListAsync

-0.52

GMENT

-0.52

POSITIVE LOGITS

 Partagez

0.53

 Carrasco

0.52

Annexes

0.50

MockMvc

0.49

 Tetrahedron

0.48

 Rubens

0.48

Bronnen

0.48

 Ringo

0.47

 kijk

0.47

ensburg

0.47

Activations Density 4.739%

words relating to future possibility

possibility and uncertainty

No Comments

No Known Activations