INDEX

Explanations

mathematical equations and notation

oai_token-act-pair · gemini-2.0-flash

[

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

-1.65

eg

-0.71

ed

-0.69

е

-0.68

ez

-0.66

-0.65

et

-0.61

ee

-0.57

ek

-0.56

el

-0.56

POSITIVE LOGITS

 itſelf

1.07

 myſelf

1.05

 pleaſure

1.04

 ſeveral

1.01

ſelf

1.00

 themſelves

0.99

 purpoſe

0.98

 raiſ

0.96

 Jefus

0.94

ſelves

0.93

Activations Density 2.743%

mathematical equations and notation

[

No Comments

No Known Activations