INDEX

Explanations

terms related to media, societal groups, and political entities

oai_token-act-pair · gemini-2.0-flash

Hollywood

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

dAtA

-0.57

ftagPool

-0.57

 GenerationType

-0.56

WillAppear

-0.53

 strcmp

-0.53

 resourceCulture

-0.53

mitian

-0.52

 beginnetje

-0.51

 समीक्षक

-0.51

 initComponents

-0.50

POSITIVE LOGITS

writeFieldEnd

0.59

̀nh

0.56

StatusBadRequest

0.55

cluye

0.52

----</

0.51

 <>",

0.50

EndContext

0.50

Демографія

0.49

pillars

0.48

ografija

0.48

Activations Density 2.706%

terms related to media, societal groups, and political entities

Hollywood

No Comments

No Known Activations