INDEX

Explanations

punctuation and discourse markers, particularly those at the end of sentences or clauses and words having to do with news or events

oai_token-act-pair · gemini-2.0-flash

Seems to activate at the end of sentences or code blocks

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

Protests and demonstrations

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

 kasarigan

-0.81

principalColumn

-0.71

 Audiodateien

-0.70

 endblock

-0.68

ContentAlignment

-0.67

endphp

-0.66

tanleria

-0.66

attended

-0.65

 CreateTagHelper

-0.63

 Particip

-0.63

POSITIVE LOGITS

heim

0.42

 Double

0.41

iset

0.41

ουσ

0.41

ут

0.40

绕

0.40

<?>>

0.40

tex

0.40

uasaan

0.40

dup

0.40

Activations Density 2.627%

punctuation and discourse markers, particularly those at the end of sentences or clauses and words having to do with news or events

Seems to activate at the end of sentences or code blocks

Protests and demonstrations

No Comments

No Known Activations