INDEX

Explanations

the letter E at the beginning of a line, possibly followed by other characters

oai_token-act-pair · gemini-2.0-flash

E or s

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

 vPvB

-0.71

 Karol

-0.65

gameserver

-0.63

SourceChecksum

-0.63

>>()

-0.63

 Radial

-0.62

 Murders

-0.62

 Shrimp

-0.62

 Elev

-0.62

Pow

-0.60

POSITIVE LOGITS

 travailleurs

0.58

 prisonniers

0.56

 enfans

0.54

 médicaux

0.52

 générations

0.51

 récompenses

0.51

 espirituales

0.50

 soins

0.50

 vostri

0.49

 supérieurs

0.49

Activations Density 2.622%

the letter E at the beginning of a line, possibly followed by other characters

E or s

No Comments

No Known Activations