INDEX

Explanations

articles, stories, and episodes of shows

oai_token-act-pair · gemini-2.0-flash

Movie/TV events

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

kháu

-0.63

reportWebVitals

-0.62

رشف

-0.60

-------

-0.57

SupportActionBar

-0.57

AnchorTagHelper

-0.57

Manbalar

-0.57

SuppressMessage

-0.56

tagext

-0.56

makeText

-0.56

POSITIVE LOGITS

 nationaux

0.46

rítica

0.46

hatikan

0.46

 naturels

0.45

 /\.(

0.44

 trône

0.44

mdi

0.43

erede

0.43

umoj

0.43

 NSCoder

0.43

Activations Density 6.747%

articles, stories, and episodes of shows

Movie/TV events

No Comments

No Known Activations