INDEX

Explanations

words related to computer architecture and memory management

oai_token-act-pair · gemini-2.0-flash

memory caches and data

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

 ModelExpression

-0.90

లాలు

-0.87

 ujednoznacz

-0.87

 Италијани

-0.81

 Roskov

-0.81

thâu

-0.80

 Bourgoin

-0.79

WriteTagHelper

-0.79

+#+#

-0.77

 Administrativna

-0.74

POSITIVE LOGITS

nyk

0.41

men

0.36

 stalls

0.35

ில

0.35

列

0.35

LR

0.34

fal

0.34

RID

0.34

вре

0.34

VSS

0.34

Activations Density 4.159%

words related to computer architecture and memory management

memory caches and data

No Comments

No Known Activations