INDEX

Explanations

words with a negative "un" prefix, words near "fore", words including "Defic", and some other legal terms

oai_token-act-pair · gemini-2.0-flash

un

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

istoitu

-0.67

setViewportView

-0.67

تقاوى

-0.63

RUnlock

-0.63

 AssemblyProduct

-0.61

 endregion

-0.61

Gambas

-0.60

存于互联网档案馆

-0.59

AlterField

-0.59

 дописавши

-0.58

POSITIVE LOGITS

reated

0.56

ups

0.54

rophoresis

0.52

secured

0.51

ify

0.50

folded

0.50

ranslated

0.50

DialogInterface

0.49

fortunate

0.48

biased

0.48

Activations Density 2.832%

words with a negative "un" prefix, words near "fore", words including "Defic", and some other legal terms

un

No Comments

No Known Activations