INDEX

Explanations

explanations or reasons for something in studies

oai_token-act-pair · gemini-2.0-flash

for this

np_token-act-pair-logits · gemini-2.0-flash

explain/for

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 &___

-0.79

 Normdatei

-0.74

 AssemblyTitle

-0.70

 utafitiHapana

-0.68

 varargin

-0.66

]:

-0.66

########.

-0.65

//});

-0.65

AndEndTag

-0.65

 reaſon

-0.63

POSITIVE LOGITS

 colspan

0.49

pellier

0.49

StatusBar

0.41

 respecting

0.41

зец

0.40

jsii

0.39

bumptech

0.39

各国

0.39

 Portuguesa

0.39

 confir

0.37

Activations Density 2.191%

explanations or reasons for something in studies

for this

explain/for

No Comments

No Known Activations