INDEX

Explanations

the names of countries or regions when capitalized

oai_token-act-pair · gemini-2.0-flash

Northern

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ―――――

-0.96

ModelSerializer

-0.88

SupportActionBar

-0.86

ſelf

-0.84

Efq

-0.82

 AssemblyCulture

-0.81

ſelves

-0.80

NewUrlParser

-0.79

itinéraire

-0.79

 ་་

-0.79

POSITIVE LOGITS

ors

0.35

0.33

ness

0.32

or

0.32

0.30

wijs

0.30

ál

0.30

猟

0.28

чества

0.28

álás

0.28

Activations Density 0.894%

the names of countries or regions when capitalized

Northern

No Comments

No Known Activations