INDEX

Explanations

references to sections within a document

oai_token-act-pair · gemini-2.0-flash

referencing sections

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

Ver

-0.88

Kon

-0.87

Mer

-0.86

Mat

-0.84

Sen

-0.84

Dec

-0.81

Col

-0.81

Per

-0.81

Pro

-0.80

Val

-0.80

POSITIVE LOGITS

цездатний

1.03

 <<<<<<<<<<<<<<

0.91

MessageTagHelper

0.91

SourceChecksum

0.88

ंदीखरीदारी

0.83

RTEE

0.82

 صوتيه

0.82

 Monfieur

0.79

 Administrativna

0.79

ValueStyle

0.78

Activations Density 2.467%

references to sections within a document

referencing sections

No Comments

No Known Activations