INDEX

Explanations

fragments of HTML or URLs from untrustworthy websites

oai_token-act-pair · gemini-2.0-flash

Website snippets

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

 room

-0.94

 rooms

-0.79

room

-0.66

 rentals

-0.65

 residence

-0.64

 accommodation

-0.64

 facility

-0.61

 facilities

-0.60

 lodging

-0.59

 szob

-0.58

POSITIVE LOGITS

HttpMethod

0.48

batore

0.47

braio

0.47

UALA

0.47

 Giovan

0.45

 électron

0.45

expandindo

0.44

 تضيفلها

0.44

(())

0.44

 Himo

0.44

Activations Density 9.643%

fragments of HTML or URLs from untrustworthy websites

Website snippets

No Comments

No Known Activations