INDEX

Explanations

words relating to phones, email and apps

oai_token-act-pair · gemini-2.0-flash

check

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 يتيمه

-0.93

 intptr

-0.70

 Meksiku

-0.69

-0.68

\}\\

-0.68

Сло

-0.65

SourceChecksum

-0.65

 Diſ

-0.63

TypedDataSet

-0.61

 Velo

-0.60

POSITIVE LOGITS

 check

1.06

 checking

1.04

check

0.98

 checks

0.91

Check

0.91

 Check

0.88

 Checking

0.88

 checked

0.86

Checking

0.86

checking

0.85

Activations Density 1.910%

words relating to phones, email and apps

check

No Comments

No Known Activations